dna-extraction

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a comprehensive utility for narrative analysis and adaptation. All logic is contained within standard instructions and locally executed Deno scripts.
  • [COMMAND_EXECUTION]: The skill includes documentation for running local Deno scripts (extract-functions.ts, emotional-beat-map.ts, structural-stylistic.ts). These scripts are used for template generation and data validation. They are executed with restricted permissions (--allow-read, --allow-write), do not perform network operations, and do not access sensitive system directories.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze descriptions of creative works (TV, film, books) and structured JSON extractions. While processing external narrative data is a potential injection vector, this is the primary functionality of the skill, and the provided scripts contain no patterns that would facilitate the execution of hidden instructions.
  • [DATA_EXPOSURE]: No hardcoded credentials, sensitive file paths, or unauthorized network operations were found. The skill operates entirely within the user's project directory for saving extraction libraries.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 11:09 AM
Security Audit — agent-trust-hub — dna-extraction