legal-writing

Pass

Audited by Gen Agent Trust Hub on Jul 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were identified in the instructions or the workflow.
  • [PROMPT_INJECTION]: The skill includes explicit instructions and hard rules to resist user requests for ghostwriting or rewriting. These internal guardrails reinforce educational integrity rather than bypassing safety protocols.
  • [DATA_EXFILTRATION]: The skill reads from and appends to local files in the ~/.claude/plugins/config/ directory. These operations are limited to the plugin's internal configuration and tracking folders for student feedback, with no evidence of network transmission or access to sensitive system credentials.
  • [COMMAND_EXECUTION]: No shell commands, dynamic code execution, or subprocess calls are present in the skill's logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 12, 2026, 01:02 AM
Security Audit — agent-trust-hub — legal-writing