github-readme-generator

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates locally using predefined Markdown templates and project file analysis to generate documentation. No indicators of malicious intent, data exfiltration, or unauthorized command execution were found.
  • [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes project files which could contain malicious instructions. This is a low-risk inherent characteristic of tools that analyze external content.
  • Ingestion points: Project configuration files (e.g., package.json, go.mod, pom.xml) and directory structure analysis mentioned in SKILL.md.
  • Boundary markers: Absent; the skill relies on the agent's contextual understanding to parse file data rather than explicit delimiters.
  • Capability inventory: File reading for metadata extraction and generating text output based on findings.
  • Sanitization: No explicit sanitization or instruction to ignore embedded commands in the source files is provided.
  • [SAFE]: Templates and examples include the author's (wwwzhouhui) WeChat ID, email, and donation QR codes hosted on a Tencent Cloud COS bucket. As these resources belong to the vendor's infrastructure and identity, they are documented as neutral vendor resources.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 05:54 PM