writing-humanize

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXFILTRATION]: The skill uses the Read, Glob, and Grep tools to access local project files. No network operations or external data transfer mechanisms were found.
  • [PROMPT_INJECTION]: The instructions include a directive to ignore command-line arguments to enforce an interactive setup process.
  • [PROMPT_INJECTION]: An indirect prompt injection surface is present as the skill processes untrusted text from files or user input. This is mitigated by a mandatory user review step before the agent applies changes to the filesystem.
  • Ingestion points: Files read via the Read tool or text provided via AskUserQuestion.
  • Boundary markers: None identified.
  • Capability inventory: The skill utilizes the Write and Edit tools.
  • Sanitization: No automated sanitization is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 12:48 PM