skills/mr-kelly/skills/kelly-writer/Gen Agent Trust Hub

kelly-writer

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes Node.js scripts (scripts/generate_batch.mjs, scripts/export_decisions.mjs, scripts/setup.mjs) to manage content ingestion, database synchronization, and local file exports. These are intended functionalities of the content workflow.\n- [DATA_EXPOSURE_AND_EXFILTRATION]: The export utility in scripts/lib/content-assets.mjs implements strict directory boundary checks (isInside) using resolved paths to ensure image packaging operations do not access files outside the authorized project root, protecting against directory traversal attacks.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted source data via scripts/generate_batch.mjs. It mitigates injection risks by implementing a mandatory human-review workflow in the companion UI, employing sanitization via slugify in scripts/lib/text.mjs, and scoping agent capabilities to specific Busabase API operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 10:36 AM
Security Audit — agent-trust-hub — kelly-writer