doc-validator
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONNO_CODEPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to execute multiple Python-based validation scripts (e.g., validate_all.py, validate_links.py) located in ai_dev_flow/scripts/ to perform cross-document checks.
- [NO_CODE]: Although the skill is built around the execution of validation logic, the actual source code for the referenced Python scripts is not included in the provided skill files, preventing a full security audit of the execution logic.
- [PROMPT_INJECTION]: The skill processes user-provided documentation files from a specified docs_path, which introduces a surface for indirect prompt injection.
- Ingestion points: Documentation files contained within the directory provided to the docs_path input variable.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands within the documentation are defined in the skill configuration.
- Capability inventory: The skill utilizes subprocess calls to execute Python scripts that parse and analyze document content.
- Sanitization: There is no evidence of content sanitization or validation to prevent the agent from following instructions embedded maliciously within the processed documentation.
Audit Metadata