brief-section-drafter

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs local file reads from the ~/.claude/plugins/config/ directory. This is used to load case theory and internal style guidelines from CLAUDE.md, which is a standard practice for context-aware legal drafting tools and does not involve sensitive system files.\n- [PROMPT_INJECTION]: The skill processes untrusted user data regarding legal cases, creating a surface for indirect prompt injection. However, since the skill has no functional capabilities to write to the file system, execute commands, or communicate over a network, the risk is negligible and does not warrant a higher severity.\n
  • Ingestion points: Case facts and section requirements provided by the user in SKILL.md.\n
  • Boundary markers: None identified.\n
  • Capability inventory: No subprocess calls, exec/eval, file-write, or network operations found in SKILL.md.\n
  • Sanitization: No input validation or sanitization is performed on user inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 07:07 AM
Security Audit — agent-trust-hub — brief-section-drafter