session-resume
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFE
Full Analysis
- Command Execution (SAFE): The skill executes local scripts (./scripts/log-skill.sh, ./scripts/compound-dashboard.sh) and standard commands (ls, git) to retrieve session data. These operations are restricted to the local environment and match the skill's description.\n- Indirect Prompt Injection (SAFE): The skill reads content from local directories (todos/, plans/, docs/solutions/) to gather context. While reading external data is a surface for indirect prompt injection, this is the core intended functionality and no dangerous downstream capabilities were identified in the provided code.
Audit Metadata