good-docs-audit
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is focused on text analysis and documentation review. Analysis of the instructions and the audit process confirmed that the skill does not attempt to access sensitive system files, hardcode credentials, or execute arbitrary shell commands.- [PROMPT_INJECTION]: The skill processes untrusted documentation files (READMEs, guides), which represents a surface for Indirect Prompt Injection. However, the instructions mandate a strict reporting structure, requiring the agent to cite specific file lines and quote exact text. This structured approach, combined with the lack of high-privilege tools (like network access or administrative commands), effectively mitigates the risk of the agent following instructions embedded within the audited text.
Audit Metadata