session-retro
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions designed to influence the agent's environment recommendations.
- Ingestion points: The skill reads session transcripts, logs, and user account data in 'SKILL.md' (Workflow Step 1) to identify failures.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands within the processed logs are present in the provided files.
- Capability inventory: Based on findings, the skill is authorized to propose changes to high-impact artifacts including 'AGENTS.md', lint rules, typechecks, tests, pre-commit hooks, and CI jobs ('SKILL.md' Workflow Step 2).
- Sanitization: There are no explicit instructions for the agent to sanitize or validate the content of session logs before using them to formulate environment improvements.
Audit Metadata