legal-writing

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs standard file read and write operations within a local configuration directory (~/.claude/plugins/config/) to manage student profiles and historical feedback. These operations do not target sensitive system credentials or protected directories.
  • [SAFE]: No evidence of remote code execution, external script downloads, or network exfiltration was found. The skill operates entirely on local context and user-provided drafts.
  • [SAFE]: While the skill processes user-provided drafting text, it lacks any high-privilege capabilities (such as shell access or network requests) that could be exploited via indirect prompt injection. The skill's instructions strictly prohibit rewriting content, further limiting potential misuse.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 03:58 PM
Security Audit — agent-trust-hub — legal-writing