investigation-memo
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection Surface: The skill processes data from investigation logs to generate and update memos. When an agent processes untrusted external data, there is a potential risk that instructions embedded within that data could influence the agent's output or behavior.
- Ingestion points: The skill reads from an "investigation log" mentioned in SKILL.md.
- Boundary markers: The instructions do not specify the use of delimiters or specific tags to separate data from instructions.
- Capability inventory: The skill is designed to draft and update text-based investigation memos based on log data.
- Sanitization: There are no explicit instructions to sanitize or validate the content of the investigation log before processing.
Audit Metadata