editorial-ops

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [No Code] (SAFE): The skill is composed of markdown templates and guidelines with no executable scripts or command-line utilities.
  • [Indirect Prompt Injection] (LOW): The skill describes workflows involving the processing of external web and document data. Evidence: 1. Ingestion points: Playwright captures landing pages and gated assets; Context7 fetches external GA4/HubSpot documentation. 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the templates. 3. Capability inventory: Serena patches CMS snippets; Playwright interacts with web pages. 4. Sanitization: No sanitization of ingested external content is mentioned in the provided documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:20 PM