yy-create-readme

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from the local project environment to generate documentation.
  • Ingestion points: The skill reads contents from project configuration files (e.g., package.json, pom.xml, requirements.txt) and existing README.md files in Steps 1, 2, and 3.
  • Boundary markers: There are no defined delimiters or specific instructions provided to the agent to ignore or isolate potentially malicious instructions embedded within the scanned project files.
  • Capability inventory: The skill has the capability to scan the project directory, read multiple file types, and perform file-write operations to the project's root README.md (Step 6).
  • Sanitization: The skill does not implement sanitization, escaping, or validation of the content gathered from the project files before interpolating it into the prompt for README generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 06:33 AM