generate-instructions

Pass

Audited by Gen Agent Trust Hub on May 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a utility for generating documentation through local directory analysis. It does not exhibit any patterns of data exfiltration, unauthorized network access, or command execution from untrusted sources.
  • [PROMPT_INJECTION]: The skill ingests content from files in a target directory to generate summaries, which creates a surface for Indirect Prompt Injection. However, this is inherent to the skill's purpose, and the risk is considered low because the output is restricted to a markdown template and intended for human review. Ingestion points: files within the specified target directory. Boundary markers: none. Capability inventory: file-system read access (analysis) and write access (generating CLAUDE.md). Sanitization: none.
Audit Metadata
Risk Level
SAFE
Analyzed
May 7, 2026, 09:40 PM
Security Audit — agent-trust-hub — generate-instructions