agent-context-manager
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to manage and retrieve external knowledge documents which are then processed by agents. This creates an inherent surface for indirect prompt injection if the stored documents (body field) contain malicious instructions.
- Ingestion points: The
fetchandlistactions inSKILL.mdretrieve document content (body) that the agent is expected to follow. - Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore embedded commands within the fetched context documents.
- Capability inventory: The tool provides 11 actions for document lifecycle management (create, update, fetch, etc.) as detailed in
schema.md. - Sanitization: No explicit sanitization or validation of the document
bodyis mentioned before it is loaded into the agent's context.
Audit Metadata