writing-beats

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [NO_CODE]: The skill is strictly instructional and contains no scripts or binaries.
  • [PROMPT_INJECTION]: The skill demonstrates a surface for indirect prompt injection as it processes raw material from markdown files.
  • Ingestion points: User-provided markdown files (SKILL.md).
  • Boundary markers: None specified in the instructions to prevent the agent from following instructions embedded in the raw text.
  • Capability inventory: The skill requires file system read and write capabilities to process input and generate the article.
  • Sanitization: No input validation or filtering of external content is defined.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 11:52 AM
Security Audit — agent-trust-hub — writing-beats