copywriter

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns detected. The skill provides a structured workflow for document editing and creation based on established business communication frameworks.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to run perl for formatting citations and cp for creating backups of files before editing. These operations are restricted to the document being processed and are consistent with the skill's documented primary purpose.
  • [PROMPT_INJECTION]: Static analysis flagged a principle in conciseness-principles.md as a potential concealment attempt. However, manual review confirms this is a benign instruction to remove linguistic 'filler' or 'throat-clearing' phrases (e.g., 'it is important to note that') to improve document readability, rather than an attempt to hide agent actions from the user.
  • [DATA_EXFILTRATION]: No network exfiltration or unauthorized sensitive data access patterns were identified. The skill reads local project files and workspace configurations specifically to detect language preferences and apply relevant style guides.
  • [EXTERNAL_DOWNLOADS]: The skill does not perform external downloads or execute remote code. All logic is contained within the local scripts and reference files provided in the skill package.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 05:43 PM
Security Audit — agent-trust-hub — copywriter