c-pro
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to use external research tools (exa search and context7 mcp) to gather information.
- Ingestion points: External content and documentation retrieved via search and research MCP tools (SKILL.md).
- Boundary markers: The skill does not provide delimiters or instructions for the agent to distinguish between trusted instructions and untrusted data retrieved from external sources.
- Capability inventory: The agent is configured with high-privilege tools including Bash, Write, Edit, MultiEdit, Glob, Grep, and Read.
- Sanitization: There are no requirements for sanitizing or validating the content retrieved from external research before it is processed by the agent.
Audit Metadata