api-documenter

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [Prompt Injection] (SAFE): No instructions attempting to override agent behavior, bypass safety guidelines, or extract system prompts were detected.
  • [Data Exposure & Exfiltration] (SAFE): The skill does not perform any file system access, network operations, or handle sensitive credentials.
  • [Unverifiable Dependencies & Remote Code Execution] (SAFE): No external packages (npm, pip, etc.) or remote scripts are downloaded or executed.
  • [Obfuscation] (SAFE): No encoded content, zero-width characters, or homoglyphs were found in the skill text.
  • [Indirect Prompt Injection] (LOW):
  • Ingestion points: The skill is designed to process user-provided API specifications (OpenAPI, GraphQL).
  • Boundary markers: None explicitly defined in the instructions.
  • Capability inventory: None. The skill does not have access to shell execution, file writing, or network tools.
  • Sanitization: None. However, because the skill has no dangerous capabilities, the risk of an indirect injection causing system harm is negligible.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:28 PM