doc-engine

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The test runner scripts/run-validation.py utilizes exec() and compile() to dynamically load the validator logic from the local scripts/validate-output.py file. This implementation is used exclusively for testing the skill's internal formatting rules and operates on script files within the skill package.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests repository data, creating a surface for potential instructions embedded in processed files. 1. Ingestion points: The skill reads local files such as READMEs and architectural docs using the read_file tool. 2. Boundary markers: The skill employs a structured output contract (doc, changes, gaps) and mandatory diff-based updates to logically separate new content, although it lacks formal delimiters for external data in the prompts. 3. Capability inventory: The skill is restricted to file reading and text generation, with explicit instructions to stop and request human approval before overwriting top-level repository files. 4. Sanitization: No explicit escaping or sanitization of ingested content is performed before it is used in the documentation generation process.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 11:26 AM