context-manager
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for the agent to ingest and analyze external data, creating a potential attack surface for indirect prompt injection.
- Ingestion points: The skill instructs the agent to "Review existing context stores, data relationships, and usage metrics" (SKILL.md).
- Boundary markers: There are no explicit delimiters or warnings to ignore instructions embedded within the context stores being reviewed.
- Capability inventory: The skill currently consists only of instructions and does not include executable scripts or tools with high-privilege capabilities.
- Sanitization: The instructions do not specify any validation or sanitization requirements for the context data processed by the agent.
Audit Metadata