ai-social-pro

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates automated audience engagement, including DM automation and comment management, which creates a surface where external users could potentially inject malicious instructions into the agent's workflow.
  • Ingestion points: Social media comments and direct messages are ingested as untrusted data for processing (SKILL.md).
  • Boundary markers: No specific delimiters or boundary markers are defined to isolate external content from the agent's core instructions.
  • Capability inventory: The skill identifies capabilities for auto-publishing and automated message responses.
  • Sanitization: No explicit sanitization or validation logic for external input is provided in the documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 11:32 PM
Security Audit — agent-trust-hub — ai-social-pro