agent-ready
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze external data from origin servers, which creates a vulnerability surface for indirect prompt injection.
- Ingestion points: The agent is directed in Phase 4 of
SKILL.mdand the 'Verify' sections of the reference files to performGETrequests on external URLs (e.g.,/.well-known/agent-card.json,/auth.md,/openapi.json) to record their status and contents. - Boundary markers: The instructions do not define explicit delimiters or 'ignore embedded instructions' warnings for the data fetched from these external origins.
- Capability inventory: The skill uses network operation capabilities (
GETrequests) to reach external domains. - Sanitization: There is no mention of sanitizing or escaping the content retrieved from these external documents before the agent processes them for the final 'Reply contract'.
Audit Metadata