apilookup
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill retrieves documentation and package metadata from well-known and official sources, including GitHub repositories (e.g., Facebook, Angular, Google, Microsoft), package registries (PyPI, npm, crates.io), and official cloud documentation domains (e.g., cloud.google.com). These network operations are conducted using standard search and fetch tools and are strictly limited to the skill's lookup functionality.
- [PROMPT_INJECTION]: The skill has an ingestion surface for untrusted data by fetching content from the web to synthesize documentation answers. This is an inherent risk common to lookup-based skills.
- Ingestion points: Content retrieved via
WebFetchandWebSearchtools during Tier 2 (Targeted) and Tier 3 (Arbitrary) lookup operations. - Boundary markers: The instructions lack explicit delimiters (e.g., XML blocks) or "ignore instructions" warnings for the agent when processing the fetched text.
- Capability inventory: The skill uses tools for network retrieval and documentation search. It does not perform sensitive file access, shell command execution, or file-system writes.
- Sanitization: There is no specific evidence of sanitization or filtering of external content before it is processed by the agent.
Audit Metadata