product-description

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides a structured methodology for generating technical documentation by analyzing external source code and running applications.
  • [COMMAND_EXECUTION]: The skill includes a local utility script, references/check-links.py, used to validate the integrity of documentation links. The script performs local file reads and regex matching without network access or unsafe execution patterns.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves analyzing untrusted data (external source code and tests). While this presents an attack surface for indirect prompt injection, it is the intended purpose of the skill and the risk is mitigated by the agent's internal safety guardrails.
  • Ingestion points: Source code, test suites, and UI definitions analyzed during the documentation phases.
  • Boundary markers: The skill does not explicitly define delimiters for external content within the generated documentation.
  • Capability inventory: The agent is tasked with file creation, reading source files, and executing the provided link-checking script.
  • Sanitization: No explicit content sanitization is described in the prompt instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 01:46 AM