ap2-risk-signals
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions specify fetching live documentation from
https://ap2-protocol.org/ap2/specification/andhttps://ap2-protocol.org/ap2/security_and_privacy_considerations/. This is used to inform the implementation of the risk framework. - [INDIRECT_PROMPT_INJECTION]: The skill creates an attack surface for indirect prompt injection by fetching and processing untrusted external data from the web.
- Ingestion points: Documentation URLs and web search results specified in
SKILL.md. - Boundary markers: No explicit delimiters or warnings to ignore embedded instructions are present for the fetched content.
- Capability inventory: The skill is configured with
Write,Edit, andBashtools, allowing file system modification and command execution based on processed data. - Sanitization: No sanitization or validation of the external content is performed before it enters the agent's context.
Audit Metadata