retro
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze "session logs" (SKILL.md), which may contain untrusted data or command outputs from previous activities that could attempt to influence the agent's analysis during the retrospective process.
- Ingestion points: The skill explicitly directs the agent to search through and read session logs on the local machine (SKILL.md, Step 2).
- Boundary markers: There are no instructions provided to the agent to treat log content as untrusted or to use specific delimiters when processing this data.
- Capability inventory: The agent utilizing this skill typically has capabilities to read and write repository configuration files such as
AGENTS.md,CODING_STANDARDS.md, and project documentation. - Sanitization: The instructions do not define any sanitization, filtering, or validation steps for the content found within the session logs.
Audit Metadata