session-context
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill's operations are restricted to reading and writing local state files (.claude/ACTIVE_CONTEXT.md and .claude/DECISIONS.md). This behavior aligns with its stated purpose of session persistence and does not involve unauthorized access to sensitive system files, environment variables, or external network resources.
- [NO_CODE]: The skill is implemented entirely through markdown-based instructions for the agent. There are no associated scripts, binaries, or package dependencies (Python or Node.js) included, which significantly minimizes the attack surface.
Audit Metadata