writing-humanizer

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill suggests running a system command for validating document edits.
  • Evidence: The file 'SKILL.md' instructs the agent to run 'git diff --check -- ' when available to confirm that claim truth values are preserved after editing.
  • [PROMPT_INJECTION]: The skill processes user-provided content, presenting an indirect prompt injection surface.
  • Ingestion points: The skill primarily ingests 'user-provided drafts' and 'nearby provided context' as specified in 'SKILL.md'.
  • Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions within the user-provided text.
  • Capability inventory: The skill is capable of modifying files directly and executing git commands.
  • Sanitization: No validation or sanitization of the input text is required by the instructions before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 07:44 AM
Security Audit — agent-trust-hub — writing-humanizer