get-api-docs
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from external documentation sources which could potentially contain malicious instructions intended to hijack the agent's logic during code implementation or verification.
- Ingestion points: External supplier documentation websites and community-curated content retrieved via the
chubCLI tool as described in the Workflow (SKILL.md). - Boundary markers: There are no explicit instructions to use delimiters or specific prompt headers to isolate the retrieved documentation from the agent's internal reasoning or system instructions.
- Capability inventory: The skill is authorized to modify local project source code and execute subprocesses for verification purposes, such as "minimal API client smoke" tests, based on the external documentation (SKILL.md, Workflow step 5).
- Sanitization: Although the skill includes safeguards against using placeholder credentials and "mechanical copying" of examples, it lacks a formal mechanism for sanitizing or escaping instructions embedded within the retrieved documentation before they are processed by the agent.
Audit Metadata