messaging-compliance-checker

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is a non-executable markdown document. It does not contain any scripts, binary files, or commands that could be executed on the host system.
  • [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it is designed to ingest and process untrusted 'Copy text' provided by users.
  • Ingestion points: The 'Copy text' input field in SKILL.md.
  • Boundary markers: None present; the skill does not instruct the agent to use delimiters like XML tags or triple quotes to isolate the content being reviewed.
  • Capability inventory: The agent generates a structured textual 'COMPLIANCE REVIEW' verdict.
  • Sanitization: No sanitization or validation of the input text is specified.
  • [SAFE]: The external link to the author's GitHub repository (github.com/sboghossian/mini-claude-for-legal) is a standard attribution reference and does not involve remote code execution or data exfiltration.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 02:50 PM
Security Audit — agent-trust-hub — messaging-compliance-checker