Skill Detail

Context Agent

This skill saves session summaries, decisions, and pending tasks to enable session continuity. It also loads automatic briefings in the next session.

GitHub:sickn33/antigravity-awesome-skills context-agent
version 2984d26f90b5
static analysis only
no human review yet
Use Caution

Current public label

Use Caution

Because the skill references secrets and has broken references, it is labeled with caution.

This label is currently coming from the automated scorecard.

Automated result

Use Caution

Driftloom found broken references and a reference to credentials or secrets.

1 medium, 3 low Final label: use caution.

Human review

No human review has been recorded yet.

The current public label is still relying on automation. A human has not weighed in yet.

What happened

Driftloom completed a static scan. It inspected the skill files, recorded findings, and generated a scorecard.

Runtime evidence

No sandbox runtime result has been recorded yet.

What did not happen

  • Driftloom did not run this skill in an isolated sandbox yet.
  • This label is not a guarantee that the skill is safe, bug-free, or appropriate for every environment.
  • A good score does not replace human judgment when a skill touches secrets, shell access, or external systems.

Source provenance

Source: Workspace import

Originally ingested from a local workspace copy.

Scorecard

Safety
85
Quality
82
Transparency
100
Operational
92
Maintenance
76

1 medium, 3 low Final label: use caution.

Severity mix: 1 medium, 3 low

What Driftloom checked

  • Read the skill files and metadata to understand what the skill claims to do.
  • Looked for shell commands and risky command patterns, even if none stood out strongly.
  • Looked for external URLs and network behavior.
  • Looked for secret, token, password, and credential references.
  • Checked for broken internal references and missing files.

Findings

Secret or credential reference detected
secret.reference · safety
Medium

The source references credentials or secret material in executable or configuration context.

File: scripts/session_parser.py
Evidence: Token
Broken relative reference detected
reference.missing_relative_path · quality
Low

The source references `session-NNN-1.md`, but that path does not exist.

File: references/context-format.md
Evidence: *Sessão anterior: [session-NNN-1](session-NNN-1.md)*
Broken relative reference detected
reference.missing_relative_path · quality
Low

The source references `args`, but that path does not exist.

File: scripts/context_manager.py
Evidence: commands[args.command](args)
Broken relative reference detected
reference.missing_relative_path · quality
Low

The source references `session-{prev:03d}.md`, but that path does not exist.

File: scripts/session_summary.py
Evidence: lines.append(f"*Sessão anterior: [session-{prev:03d}](session-{prev:03d}.md)*")