api-documentation-verify

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and process the contents of various files within a repository which may contain untrusted data.
  • Ingestion points: The skill discovers and reads documentation files (e.g., .md, README, DOCS, API) and referenced source code files to extract and verify technical claims.
  • Boundary markers: The instructions do not define boundary markers or delimiters to isolate untrusted file content, nor do they instruct the agent to ignore any embedded instructions found within those files.
  • Capability inventory: The skill leverages file search (find) and read capabilities. It performs text extraction and comparison but does not exhibit capabilities for executing analyzed code or performing network operations.
  • Sanitization: There is no mention of sanitizing or validating the contents of the files before they are processed by the agent for verification purposes.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 07:48 AM