protocolsio-integration
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes external protocol descriptions, procedure steps, and community comments from the protocols.io API. This external content could be maliciously crafted to influence the agent's actions during processing.
- Ingestion points: Untrusted data enters the agent context through endpoints like GET /protocols and GET /protocols/{id}/comments, as defined in references/protocols_api.md and references/discussions.md.
- Boundary markers: The skill documentation lacks explicit instructions for the agent to use delimiters or ignore embedded instructions within the fetched protocol data.
- Capability inventory: The skill possesses write capabilities including protocol creation (POST /protocols), publishing (POST /protocols/{id}/publish), and file uploads to workspaces (POST /workspaces/{id}/files/upload).
- Sanitization: No input validation or sanitization routines for the content retrieved from the protocols.io platform are specified in the provided reference materials.
Audit Metadata