readme-generator

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill ingests untrusted data from the local project environment to generate documentation, which could be exploited if source files contain hidden instructions.\n
  • Ingestion points: SKILL.md Step 1 specifies gathering information from manifest files (package.json, pyproject.toml) and scanning project source files.\n
  • Boundary markers: No specific delimiters or boundary markers are defined to separate untrusted project content from the agent's generation instructions.\n
  • Capability inventory: The skill is designed for documentation generation; while it does not directly call execution tools, the output is intended for user-facing README files.\n
  • Sanitization: There is no evidence of sanitization or filtering applied to the content extracted from the project's source files.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 01:41 AM