api-documentation
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Vulnerability Surface.
- Ingestion points: The skill is designed to process external artifacts including OpenAPI/GraphQL schemas, code annotations, and test fixtures as primary sources of truth (documented in
SKILL.mdunder Step 3). - Boundary markers: The instructions lack explicit requirements for the agent to use delimiters or security-focused boundary markers when interpolating content from these external sources into its prompts.
- Capability inventory: The skill's environment grants the agent significant file system capabilities via
Read,Write,Edit,Glob, andGreptools, which could be abused if an ingested specification contains malicious instructions. - Sanitization: There are no instructions for validating, filtering, or sanitizing the content of the ingested specifications before the agent processes them.
Audit Metadata