readme

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • Command Execution (SAFE): The skill utilizes find and cat to identify project structure and read configuration files. These are standard inspection commands necessary for documentation generation and pose no direct security threat to the system.
  • Indirect Prompt Injection (LOW): The skill ingests data from local project files (source code and manifests) to generate the README. This creates a surface for indirect prompt injection where malicious instructions hidden in code comments could influence the agent's output.
  • Ingestion points: Local source files (.py, .js, etc.) and configuration files (package.json, pyproject.toml).
  • Boundary markers: Absent; the content is ingested without explicit delimiters or safety instructions regarding embedded content.
  • Capability inventory: File reading (cat) and directory searching (find).
  • Sanitization: Absent; the skill relies on the LLM's internal safety filters to ignore instructions found within the code.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 09:34 PM