aip
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill facilitates the retrieval of official technical documentation from a trusted source to guide API design and review tasks.
- [INDIRECT_PROMPT_INJECTION]: The skill involves ingesting data from an external source to influence agent decisions. (1) Ingestion points: Documentation is fetched from https://google.aip.dev via WebFetch as described in SKILL.md. (2) Boundary markers: No explicit delimiters or boundary instructions are specified in the instructions to isolate external text from the agent context. (3) Capability inventory: The skill does not define any sensitive internal capabilities such as file writing, system command execution, or network exfiltration across its instructions. (4) Sanitization: No explicit sanitization or content validation steps are defined for the fetched documentation text.
Audit Metadata