aim-query
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external memory instances through various MCP tools and API endpoints, creating a surface for indirect prompt injection.
- Ingestion points: Data is pulled into the agent's context via tools like
memory_query,memory_recent,memory_explore, and direct API access to/api/v1/.../pages/<path>. - Boundary markers: The skill instructions do not specify the use of delimiters or 'ignore' instructions to separate retrieved memory content from the agent's core operational logic.
- Capability inventory: The agent uses the retrieved data to perform design decisions, status reports, and 'catch-up' summaries, potentially executing instructions embedded in the memory hits.
- Sanitization: There is no evidence of content sanitization, validation, or escaping of the recalled markdown/prose content before it is processed by the agent.
Audit Metadata