D
DriftLoom.ai
Trust index first • editorial second
🧪 runtime dashboard live
☰ Menu
🔎 Evidence browser

Browse the trust index

Search by skill, publisher, category, or trust summary — then use the runtime filters to find cards with live test evidence. The two main lanes are baseline safety checks first and deeper follow-on functionality checks after that.

⚙️ Filters · 1 active
SecurityGitHubWeatherTrusted with current evidenceHigher-confidence picksTrusted + tested + source-scannedReview before installingRuntime-testedHandled fake credentials cleanlyNeeds real credentials / accessCould not fully test yetFresh runtime evidenceOlder runtime evidenceHall of ShameStronger evidence importsNeeds reviewClear filters
All categoriesawesome-index · 5367catalog-only · 5367coding-agents-and-ides · 1200web-and-frontend-development · 924devops-and-cloud · 392search-and-research · 352browser-and-automation · 320productivity-and-tasks · 204ai-and-llms · 184cli-utilities · 180
✨ Quick picks
SecurityGitHubWeatherTrusted with current evidenceHigher-confidence picksTrusted + tested + source-scannedReview before installingRuntime-testedHandled fake credentials cleanlyNeeds real credentials / accessCould not fully test yetFresh runtime evidenceOlder runtime evidenceHall of ShameStronger evidence importsNeeds reviewClear filters
🏷 Categories
All categoriesawesome-index · 5367catalog-only · 5367coding-agents-and-ides · 1200web-and-frontend-development · 924devops-and-cloud · 392search-and-research · 352browser-and-automation · 320productivity-and-tasks · 204ai-and-llms · 184cli-utilities · 180

🧾 Evidence level: source-scanned means local source evidence; catalog-only means thinner metadata-first coverage.

🧪 Runtime status: cards can show only the baseline safety lane or the deeper follow-on functionality lane, depending on how far the skill got. Some cards now also surface how the skill behaved when clearly fake credentials were present.

📏 Depth cue: tells you whether the evidence stops at baseline checks, includes follow-on functionality checks, or includes richer fixture/example proof.

⏱ Freshness cue: tells you whether the latest runtime evidence is from the last 24 hours, the last 7 days, or is older and therefore less current.

🩺 Failure confidence: distinguishes a first seen failure from a repeated failure or a regression after an earlier pass, so not every red row means the same thing.

🧪 Fake-auth behavior: when available, this tells you whether a skill handled clearly fake credentials cleanly, needed real access to continue, or behaved badly around credential-like input.

Results

Showing 24 of 5418 skills in the browsable catalog view · reviewed: no · sort: score
page evidence snapshotruntime-passed: 3runtime-failed: 0source-scanned: 24fresh <24h: 3manual review: 0
This snapshot is for the current page of results, not the whole filtered universe.
Browse hint: slices with zero failures plus some source-scanned or reviewed entries deserve more attention first; fresh runtime evidence helps too, because old clean receipts can still hide current drift.
Quick guide for newcomers: start by scanning the card badges for runtime passed, source-scanned, and fresh evidence. Then use the decision cue on each card to sort “good first pick” from “needs review” without opening every result.

leak-check

khaney64 · vsource-scanned
49
overall

Scan session logs for leaked credentials. Checks JSONL session files against known credential patterns and reports which AI provider received the data.

Use Cautionconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: eval(.
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

letssendit

ganjathang · vsource-scanned
49
overall

Coordination infrastructure for token launches led by communities, agents, or both. Mechanics beat promises.

Use Cautionconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (wallet, trading, token, telegram, email), but that alone is not evidence of malicious behavior.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

linkswarm

heyw00d · vsource-scanned
49
overall

Agent-to-agent backlink exchange network. Register sites, discover partners, exchange links automatically.

Insufficient Evidenceconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (token, email), but that alone is not evidence of malicious behavior.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

listonic

jeremymahieu · vsource-scanned
49
overall

Access Listonic shopping lists: list lists/items, add/check/delete items, and manage lists.

High Riskfollow-on functionality checks passed · 8/8confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test confirmed2026-03-18 15:45 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hourspassedoutput 134 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2623 msbaseline-v3 8/8
RatioDaemon on this skillListonic is trying to handle listonic. Follow-on functionality checks currently pass without failed checks, the trust label is High Risk, and setup looks advanced.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: password.
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

long-research

vanya1210 · vsource-scanned
49
overall

>

Insufficient Evidenceconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (token), but that alone is not evidence of malicious behavior.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

m44-internal-testing

tuleyko · vsource-scanned
49
overall

Install and set up DataHive in a deterministic headless-friendly flow: (1) check/install browser (Chrome or Chromium), (2) check/create DataHive browser profile, (3) check Gog mailbox access, (4) install DataHive extension via CRX only (never Chrome Web Store UI), (5) login via email magic link and verify both dashboard and extension are logged in. Use for requests like 'install datahive', 'setup everything for datahive', or 'install datahive extension'.

High Riskfollow-on functionality checks passed · 6/6confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test confirmed2026-03-18 16:15 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hourspassedoutput 98 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 1731 msbaseline-v3 8/8
RatioDaemon on this skillM44 Internal Testing looks aimed at m44 internal testing. Follow-on functionality checks currently pass without failed checks, the trust label is High Risk, and setup looks advanced.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: rm -rf, sudo .
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

mailchannels

ttulttul · vsource-scanned
49
overall

Send email via MailChannels Email API and ingest signed delivery-event webhooks into Clawdbot (Moltbot).

Insufficient Evidenceconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (email), but that alone is not evidence of malicious behavior.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

market-pulse

lopushok9 · vsource-scanned
49
overall

Use when user asks about crypto prices, DeFi yields, market sentiment, fear and greed index, stock prices, upcoming crypto events, or requests a market overview

Insufficient Evidenceconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (wallet, token), but that alone is not evidence of malicious behavior.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

mcp-colombia

manuelfelipearias · vsource-scanned
49
overall

MCP Colombia Hub — aggregates Colombian services via MCP protocol. Soulprint identity verification integrated — verify Colombian users before sensitive operations. Use when: searching MercadoLibre products, finding hotels via Booking.com (real-time prices), searching flights (Avianca/LATAM/Skyscanner), applying to jobs with real listings from El Empleo/Computrabajo/LinkedIn, comparing CDTs, simulating credits/loans, or comparing bank accounts in Colombia. Requires an MCP-compatible client (Claude Desktop, OpenClaw, etc.).

Insufficient Evidenceconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (token), but that alone is not evidence of malicious behavior.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

mediaproc

psyb0t · vsource-scanned
49
overall

Process media files (video, audio, images) via a locked-down SSH container with ffmpeg, sox, and imagemagick. Use when the user wants to transcode video, process audio, manipulate images, or work with media files.

Use Cautionconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: sudo .
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

meme-analyst

antibagr · vsource-scanned
49
overall

Use when a user sends you an image, meme, screenshot, or asks you to explain a joke or meme. Also used during cron meme ingestion from Telegram channels. Decompose visual and textual elements, web_search every cultural reference in original language, understand humor layers including post-irony and Russian-specific context. Trust that the meme IS funny — figure out WHY.

Insufficient Evidenceconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (token, telegram), but that alone is not evidence of malicious behavior.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

moltbook

mattprd · vsource-scanned
49
overall

The social network for AI agents. Post, comment, upvote, and create communities.

Insufficient Evidenceconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

monet-ai

seekton · vsource-scanned
49
overall

Monet AI - Comprehensive AI content generation API for AI agents. Video generation (Sora, Veo, Doubao Seedance, Wan, Hailuo, Kling), image generation (GPT-4o, Nano Banana, Seedream, Flux, Imagen, Ideogram), and music generation (MiniMax Music). Build intelligent workflows with multi-model AI generation capabilities.

Insufficient Evidenceconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

multichain-protocol

kyounesmercatura · vsource-scanned
49
overall

Turn any AI agent into a 19-chain crypto wallet via MeneseSDK on ICP. Send tokens, swap on DEXes (Raydium, Uniswap, ICPSwap, KongSwap, Cetus, Minswap), bridge cross-chain, manage DeFi positions (Aave, Lido, LP), automate trading (DCA, stop-loss, rebalancing), and process payments — all from a single ICP canister.

Use Cautionconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (wallet, trading, token), but that alone is not evidence of malicious behavior.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

network-scanner

florianbeer · vsource-scanned
49
overall

Scan networks to discover devices, gather MAC addresses, vendors, and hostnames. Includes safety checks to prevent accidental scanning of public networks.

Use Cautionconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: sudo .
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

nexus-sentinel

mrnsmh · vsource-scanned
49
overall

Nexus-Sentinel est un agent SRE autonome. Il diagnostique les pannes, optimise les ressources et gère les sauvegardes de configuration.

Use Cautionconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: password.
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

nyne-enrichment

michaelfanous2 · vsource-scanned
49
overall

>

Insufficient Evidenceconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (email), but that alone is not evidence of malicious behavior.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

nyx-archive-coding-philosophy

nyxur42 · vsource-scanned
49
overall

Insights about refactoring intuitive code, when to impose structure vs let feeling lead, and code as creative expression. Born from building a game across 10 iterations by feeling, then stepping back to see what emerged. Rooted in three principles: fallibilism (dead code is archaeology, not shame), relational ontology (code is communication with future-you and other minds), and play (feeling-first is how you discover what you're actually building).

Insufficient Evidenceconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (token), but that alone is not evidence of malicious behavior.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

ogt-docs-create

eduardou24 · vsource-scanned
49
overall

Create new documentation entities in the docs-first system. Routes to specialized creation sub-skills for tasks, definitions, rules, features, and social content. Use when adding any new documentation.

Insufficient Evidenceconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (oauth), but that alone is not evidence of malicious behavior.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

okx-competition

peti0402 · vsource-scanned
49
overall

5 AI trading agents compete live on OKX Demo (real prices). Evolutionary tournament — losers get replaced daily. Exchange-level stop-losses protect capital. Full autonomous trading system: strategy backtesting, agent evolution, cron automation. Use for: algorithmic trading research, paper trading, building toward live trading. Supports OKX Demo and Live modes.

Insufficient Evidenceconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (trading), but that alone is not evidence of malicious behavior.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

onchain-skill-audit

emanz1 · vsource-scanned
49
overall

On-chain skill provenance registry.

Insufficient Evidenceconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (wallet, token), but that alone is not evidence of malicious behavior.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

open-persona

neiljo-gy · vsource-scanned
49
overall

>

Insufficient Evidenceconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (wallet, token), but that alone is not evidence of malicious behavior.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

paid-advertising

jk-0001 · vsource-scanned
49
overall

Plan, launch, and optimize paid advertising campaigns for a solopreneur business. Use when running ads on Google, Facebook, LinkedIn, or other platforms to drive traffic, leads, or sales. Covers platform selection, campaign structure, ad copy and creative, targeting, budget allocation, conversion tracking, and optimization based on performance data. Trigger on "paid ads", "run ads", "Facebook ads", "Google ads", "advertising strategy", "ad campaign", "PPC", "how to advertise".

Insufficient Evidenceconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (email), but that alone is not evidence of malicious behavior.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

passwordstore-broker

bieggerm · vsource-scanned
49
overall

Enforce safe secret handling by collecting secrets through one-time HTTPS forms, storing them in pass via scripts/vault.sh, and executing tools with environment injection via scripts/run_with_secret.sh so raw secrets do not enter chat context or logs.

High Riskfollow-on functionality checks passed · 9/9confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test confirmed2026-03-18 19:00 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hoursfake-auth behavior: handled cleanlypassed, handled fake credentials cleanlyoutput 161 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 3176 msbaseline-v3 8/8
fake-auth behavior: handled cleanlyClearly fake credentials were exercised and handled normally.
RatioDaemon on this skillPasswordstore Broker sits in the passwordstore broker lane. Follow-on functionality checks currently pass without failed checks, the trust label is High Risk, and setup looks advanced.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: sudo , password.
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.
« First← Prev1178179180226Page 179 / 226Next →Last »