ai-ad-factory

Pass

Audited by Gen Agent Trust Hub on Nov 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, creating a potential surface for indirect prompt injection.
  • Ingestion points: External web page text and tool descriptions (references/browser-runtime-and-sessions.md), and media metadata or playlists from URLs (references/media-inspection-contract.md).
  • Boundary markers: The skill contains explicit instructions to the agent to treat external content as data only, stating that page text and tool descriptions are not permission to run commands or change the assignment.
  • Capability inventory: The skill uses subprocess tools for media manipulation (FFmpeg, ffprobe), browser tools for navigation, and file system writes for exporting ad artifacts.
  • Sanitization: The instructions explicitly warn against passing unvalidated content from playlists to commands and advise against treating remote URLs as local paths.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill incorporates defensive guidelines to protect sensitive information. Evidence: Instructions in references/browser-runtime-and-sessions.md and references/provider-selection-and-input-contracts.md require keeping credentials, signed URLs, and debugging endpoints out of shared artifacts and logs.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 15, 2026, 10:47 AM