retro
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes session logs, which presents a surface for indirect prompt injection from content within those logs.
- Ingestion points: Step 2 of SKILL.md directs the agent to read primary sources and session logs from the machine.
- Boundary markers: The skill does not provide boundary markers or instructions to the agent to disregard potential commands embedded in the logs.
- Capability inventory: The agent has the ability to read various repository metadata and steering files (package.json, CLAUDE.md, AGENTS.md, CODING_STANDARDS.md) and suggests modifications to them.
- Sanitization: No sanitization or filtering of the ingested log content is described.
Audit Metadata