investigation-memo
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external investigation logs to generate memos. If these logs contain adversarial instructions, they could potentially influence the agent's output during the drafting process.
- Ingestion points: The skill instructions start by requiring the agent to load "调查日志" (investigation logs) from the local environment.
- Boundary markers: No specific delimiters or instructions are used to distinguish the investigation data from the agent's instructions, nor are there warnings to ignore instructions embedded in the data.
- Capability inventory: The skill allows the agent to synthesize, summarize, and format complex information into a formal memo structure.
- Sanitization: There is no evidence of input validation or sanitization for the content of the loaded logs.
Audit Metadata