team-marketing-campaign

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious instructions or security vulnerabilities were identified in the skill. The skill functions as a high-level coordinator for marketing-specific sub-agents.
  • [SAFE]: The skill exhibits a standard indirect prompt injection surface by interpolating user-provided briefing data into instructions for other skills. This behavior is necessary for its orchestration purpose and carries minimal risk given the documentation-focused scope.
  • Ingestion points: User-provided inputs in Phase 1 (Product, Objective, Audience, Timeline, Tone).
  • Boundary markers: No specific delimiters (like XML tags or markdown blocks) are used to isolate user data from sub-agent prompts.
  • Capability inventory: The skill performs file system writes to 'docs/campaign/' and coordinates specialized sub-skills for content creation and analytics reporting.
  • Sanitization: No input validation or escaping mechanisms are applied to user data before processing.
  • [SAFE]: The prerequisite configuration command 'copilot --allow-all --max-autopilot-continues 50' is a setup instruction for the user environment to enable autonomous agent collaboration and does not constitute a security risk within the skill's logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 02:52 PM
Security Audit — agent-trust-hub — team-marketing-campaign