retrospective
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: Executes a local Node.js script located at
.claude/hooks/scripts/evaluate-session.js. This is the core functionality of the skill for performing a session retrospective. - [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection (Category 8) because it analyzes files created or modified during the session, test results, and build history to generate recommendations.
- Ingestion points: Files modified during the session, test outputs, and build history processed by
evaluate-session.js. - Boundary markers: None explicitly defined in the
SKILL.mdfile for the script's output. - Capability inventory: Executes shell commands via
node. - Sanitization: Implementation details are handled within the
evaluate-session.jsscript, which is not provided for analysis.
Audit Metadata