team-memory-search
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and follow 'Reuse' actions from files stored in the '.agents/project-memory/entries/' directory, which may contain untrusted data.\n- Ingestion points: Memory files located in '.agents/project-memory/entries/' as described in SKILL.md.\n- Boundary markers: No explicit delimiters or 'ignore embedded instructions' warnings are provided for the ingestion of these entries.\n- Capability inventory: The skill prompts the agent to 'Try the entry's Reuse action', which could result in the agent executing instructions or commands found within the external data using other available tools.\n- Sanitization: No validation, filtering, or sanitization logic is specified for the content of the memory entries.
Audit Metadata