diataxis-doc-generator

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data such as API specifications and source code, which serves as an attack surface for indirect prompt injection. Maliciously crafted input data could attempt to divert the agent from its intended documentation tasks.
  • Ingestion points: The skill reads apiSpec (e.g., openapi.yaml) and various source code files to generate artifacts, as outlined in the Input Requirements section of SKILL.md.
  • Boundary markers: There are no explicit delimiters or instructions provided to isolate these external data sources from the agent's system prompt or operational instructions.
  • Capability inventory: The skill is granted access to the Bash, Write, Edit, Read, Glob, and Grep tools in its SKILL.md configuration.
  • Sanitization: No sanitization logic or validation steps are defined for the input content prior to processing by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 09:49 PM
Security Audit — agent-trust-hub — diataxis-doc-generator