novel-revision

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided novel manuscripts which serves as an ingestion surface for untrusted data.\n- Ingestion points: Processes novel prose and dialogue (SKILL.md).\n- Boundary markers: The instructions lack specific delimiters or instructions to ignore embedded commands within the manuscript content.\n- Capability inventory: The agent writes change records, cascade task lists, and monitoring logs based on the analyzed content (SKILL.md).\n- Sanitization: No explicit sanitization of the input manuscript data is defined.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 05:03 AM
Security Audit — agent-trust-hub — novel-revision