documentation-lookup
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill uses standard Model Context Protocol (MCP) tools for documentation retrieval. No malicious patterns, obfuscation, or unauthorized access attempts were detected.
- [PROMPT_INJECTION]: The skill processes external documentation retrieved via the query-docs tool, which represents a surface for indirect prompt injection.
- Ingestion points: Output from the query-docs MCP tool.
- Boundary markers: None specified for treating retrieved documentation as untrusted data.
- Capability inventory: The skill does not have access to dangerous capabilities such as file system writes or shell execution.
- Sanitization: The skill instructs the agent to redact sensitive information from queries sent to the external service.
Audit Metadata