sfd-schedule-posts

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill performs network operations to the Zernio API at zernio.com for account verification, media upload, and post scheduling. These requests involve transmitting data to an external service.
  • [PROMPT_INJECTION]: The skill instructs the agent to generate captions based on external video content and channel strategy, which creates a surface for indirect prompt injection.
  • Ingestion points: External video files and strategy specifications referenced in Step 3 and Step 4.
  • Boundary markers: No specific delimiters or instructions are provided to ensure the agent ignores instructions potentially embedded within the media or strategy documents.
  • Capability inventory: The skill allows the agent to perform network operations, including uploading files and creating posts on social platforms.
  • Sanitization: The instructions do not define any validation or filtering steps for the content processed from external sources before it is used to generate posts.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 01:30 AM