long-form-writer

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing untrusted data.
  • Ingestion points: Data is read from files specified via the --data and --cases arguments in scripts/generate.py.
  • Boundary markers: The skill does not use delimiters or instructions to ignore embedded commands within the ingested data.
  • Capability inventory: The skill has file-writing capabilities to save the generated content to a local path.
  • Sanitization: No sanitization or validation is performed on the external content before it is interpolated into the article template.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 01:11 AM
Security Audit — agent-trust-hub — long-form-writer