ap2-agent-authorization
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch foundational documentation and protocol specifications from
ap2-protocol.orgto guide implementation and ensure terminology accuracy.\n- [INDIRECT_PROMPT_INJECTION]: The skill incorporates external content into the agent's context, which could potentially be used to influence agent behavior.\n - Ingestion points: Fetches content from
ap2-protocol.org/ap2/agent_authorization/,ap2-protocol.org/ap2/specification/, andap2-protocol.org/glossary/using theWebFetchtool.\n - Boundary markers: The skill does not provide specific instructions to delimit or ignore instructions that might be contained within the external documentation.\n
- Capability inventory: The agent has access to
Bash,Write, andEdittools, which allow for code generation and command execution based on information retrieved from the external sites.\n - Sanitization: No sanitization or validation of the fetched external documentation content is defined in the instructions.
Audit Metadata