pii-and-compliance
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown-based instructions, guidelines, and code examples. It does not contain any executable scripts, shell commands, or automation that could be abused.
- [SAFE]: While the skill's purpose is to analyze external code diffs (a potential vector for indirect prompt injection), it does not request any tool permissions (e.g., file system writes or network access) and restricts the agent's output to a specific, predefined text template. This absence of capabilities eliminates the risk associated with processing untrusted input.
- [SAFE]: All external references (such as to the 'thrillmade' GitHub repository) are consistent with the skill's stated authorship and origin. Examples of sensitive data (e.g., truncated API keys or emails) are used strictly as illustrative placeholders for detection patterns and do not represent hardcoded credentials.
Audit Metadata