disclosure-list-andrew-bird

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill is composed solely of Markdown instructions and templates within SKILL.md and README.md. It does not contain any Python scripts, Node.js packages, or binary executables.
  • [SAFE]: No suspicious patterns, obfuscation, or malicious intent were detected. The skill's behavior is consistent with its stated purpose as a legal drafting aid.
  • [EXTERNAL_DOWNLOADS]: The documentation includes installation instructions that reference a GitHub repository (github.com/b1rdmania/claude-for-uk-legal). These are standard user-facing instructions for plugin installation and do not involve automated or hidden runtime downloads.
  • [PROMPT_INJECTION]: The skill defines a surface for processing user-supplied data (such as custodian names and document descriptions). However, as the skill possesses no exploitable capabilities—such as command execution, file system writes, or network connectivity—this ingestion surface does not pose a security risk. The skill uses structured Markdown templates and specific markers like [REGIME] and [PRIVILEGE] to maintain data boundaries.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 07:32 PM
Security Audit — agent-trust-hub — disclosure-list-andrew-bird