nda-review

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized network operations were detected in the skill instructions.
  • [DATA_EXPOSURE]: The skill accesses local configuration files and workspace data located at ~/.claude/plugins/config/claude-for-legal/. This file access is limited to its own operational directory and is used for retrieving legal guidelines and matter-specific context, which is consistent with its stated purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input in the form of NDA documents. While it has the capability to write and update its own guideline configuration (CLAUDE.md), it mitigates the risk of logic poisoning by requiring an explicit human-in-the-loop confirmation before adding any new guidelines to the file.
  • [COMMAND_EXECUTION]: No shell commands or dynamic execution patterns were identified. All operations are focused on text analysis and formatted reporting.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 07:06 AM
Security Audit — agent-trust-hub — nda-review