api-doc-writer

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from external source code files during the documentation extraction phase.
  • Ingestion points: Source code files (Go, TypeScript, Python, etc.) identified in WORKFLOW-STEPS.md and SKILL.md.
  • Boundary markers: The instructions lack explicit delimiters or "ignore embedded instructions" warnings when extracting comments and signatures from source code.
  • Capability inventory: The skill utilizes file system read/write operations and shell command execution (grep, ls, find).
  • Sanitization: There is no evidence of sanitization, validation, or escaping of the extracted source code content before it is interpolated into the markdown documentation templates.
  • [COMMAND_EXECUTION]: The skill workflow documentation provides instructions for the agent to execute shell commands to discover the project structure and public API surface.
  • Evidence: WORKFLOW-STEPS.md contains specific examples of grep, ls, and find commands designed to be run in the local environment to identify exported functions, classes, and types.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 07:47 AM