newsletter-to-video

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by processing external newsletter content.
  • Ingestion points: The skill reads full newsletter issues provided by the user in Step 1.
  • Boundary markers: There are no explicit delimiters or 'ignore' instructions specified to isolate untrusted user data.
  • Capability inventory: The skill invokes internal logic and other skills ('content-strategy:hook', 'branding-kit:brand-guidelines') to generate text outputs. It does not have access to system commands, file writes, or network operations.
  • Sanitization: No input validation or filtering of the newsletter content is performed before processing.
  • [NO_CODE]: No executable scripts or source code files are included in this skill; it consists entirely of markdown-based instructions for the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 01:33 AM