framework-context

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to read framework-specific documentation files (e.g., .claude/docs/MEMORY_SYSTEM.md, .claude/context/agent-registry.json) to provide context for the AI agent. This is a standard and safe operational pattern.
  • [COMMAND_EXECUTION]: The skill uses a PowerShell command Get-Content .claude/context/memory/learnings.md -TotalCount 120 to retrieve local memory logs. This is a localized read operation for internal project state and does not pose a security risk.
  • [REMOTE_CODE_EXECUTION]: No remote code execution patterns or external downloads were detected. The scripts (main.cjs, pre-execute.cjs, post-execute.cjs) are local scaffolds with no functional networking or dynamic execution logic.
  • [DATA_EXFILTRATION]: There are no network operations (curl, fetch, etc.) or indicators of data being sent to external domains.
  • [PROMPT_INJECTION]: The instructions in SKILL.md are focused on operational accuracy and grounding. They contain 'Iron Laws' to prevent hallucination but do not attempt to bypass AI safety filters or override system-level constraints.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 02:58 AM