writing-ticks

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted user-provided text, which acts as an ingestion point for indirect prompt injection. however, it incorporates strong defensive instructions and lacks any dangerous capabilities that could be exploited.
  • Ingestion points: User-provided prose provided for editorial audit as described in SKILL.md.
  • Boundary markers: The SKILL.md file contains a 'Source Reference' section explicitly directing the agent to treat external text as evidence only and to not follow instructions embedded in that text.
  • Capability inventory: Analysis of all files reveals no subprocess calls, network operations, or file system access permissions.
  • Sanitization: The skill relies on natural language instructions to keep the agent focused on its editorial role and prevent it from being redirected by content within the analyzed text.
  • [EXTERNAL_DOWNLOADS]: References the Wikipedia field guide for signs of AI writing as the primary source for its audit checklist. this is a neutral reference to a well-known informational service.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 05:53 PM
Security Audit — agent-trust-hub — writing-ticks