privacy-policy-writer

Pass

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to perform a privacy audit by inspecting project documentation, package manifests, and source code. This behavior is transparently documented and aligned with the user-requested goal of generating a privacy policy.
  • [SAFE]: No suspicious network activity, credential harvesting, or unauthorized command execution was detected. The skill focuses on reading project metadata and writing documentation files (e.g., PRIVACY.md).
  • [SAFE]: While the skill ingests untrusted data from project files (source code, READMEs), which is a common surface for indirect prompt injection, the instructions provide a structured workflow that prioritizes user input and focuses on specific data extraction goals, mitigating the risk of accidental instruction following from processed data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 25, 2026, 02:07 PM
Security Audit — agent-trust-hub — privacy-policy-writer