generate-api-collection

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to run jq or python -m json.tool to validate the syntax of generated JSON files. These are standard, local utility commands used for development workflow validation.
  • [INDIRECT_PROMPT_INJECTION]: The skill parses Rails route and controller files to generate API documentation, which presents a surface for processing untrusted data if source code contains malicious content.
  • Ingestion points: Rails route definitions and controller actions (SKILL.md).
  • Boundary markers: No specific delimiters or boundary markers are defined for the input source files.
  • Capability inventory: File system write operations for JSON collections and execution of syntax validation commands (SKILL.md).
  • Sanitization: The skill verifies the syntactic validity of the output JSON but does not specify semantic sanitization of content extracted from code comments.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 05:23 PM
Security Audit — agent-trust-hub — generate-api-collection