docs
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external documentation sources (docs.pmnd.rs) using the
ReadMcpResourceToolandget_page_contenttools. - Ingestion points: The documentation index (
docs://{lib}/index) and page content from the pmndrs documentation server. - Boundary markers: The instructions do not include specific delimiters or wrappers to separate untrusted documentation content from the agent's instructions.
- Capability inventory: The skill is restricted to reading and retrieving documentation; it does not contain capabilities for file writing, network exfiltration, or executing system commands.
- Sanitization: No explicit sanitization or validation of the documentation content is performed before processing.
Audit Metadata