ap2-vdc-framework
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to retrieve live documentation and search results from external sources including ap2-protocol.org and the wider web. This creates a vulnerability surface for indirect prompt injection if those external sources contain malicious instructions.
- Ingestion points: Specification documents and conceptual overviews fetched from ap2-protocol.org via
WebFetch, and community guides retrieved viaWebSearch. - Boundary markers: The skill does not provide clear boundary markers or instructions for the agent to ignore potentially malicious commands embedded in the external content.
- Capability inventory: The skill operates in an environment where powerful tools such as
Bash,Write, andEditare permitted, increasing the potential impact of an injection attack. - Sanitization: There are no instructions or mechanisms provided to sanitize, filter, or validate the content retrieved from the external URLs before the agent processes it.
Audit Metadata