memento
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions explicitly direct the agent to prioritize information found in the repository over the conversation history, creating a vulnerability to malicious instructions embedded in the codebase or tool outputs.
- Ingestion points: The skill reads from the working tree, the list of running processes, and the results of recently executed tools as defined in the 'Reading' section of SKILL.md.
- Boundary markers: The instructions do not specify any delimiters or safety markers to help the agent distinguish between data and potential instructions within the files it reads.
- Capability inventory: The skill leverages the agent's ability to read files, list processes, and inspect tool execution history.
- Sanitization: There is no mention of sanitization, filtering, or validation of the content retrieved from the repository state before it is processed by the agent.
Audit Metadata