docs-sync-audit
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The included utility script
scripts/docs_drift.pyexecutesgitcommands to inventory repository files and check commit history. The script implementation avoids shell execution by using argument lists, mitigating command injection risks. - [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves reading and analyzing untrusted content, such as repository documentation and source code, which serves as an ingestion point for potential malicious instructions.
- Ingestion points:
SKILL.mddefines workflows for auditing repository files, including READMEs, code comments, and configuration files. - Boundary markers: The instructions do not define explicit delimiters or 'ignore instructions' warnings for the content being audited.
- Capability inventory: The skill utilizes file system tools and a Python script to verify documentation claims; the agent also has access to shell tools.
- Sanitization: No specific input filtering or sanitization is performed on the audited content, relying on the agent's internal guardrails.
Audit Metadata