event-marketing-plan

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is purely instructional and serves the purpose of organizational planning without any hidden or malicious behaviors.
  • [SAFE]: All referenced external guidelines and sibling skills are legitimate, well-known, or belong to the skill author (samber), representing normal modular functionality.
  • [SAFE]: No instances of prompt injection, data exfiltration, obfuscation, or dangerous command execution were detected.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface via user interview responses and sibling skill data, but lacks high-privilege capabilities that would make this surface exploitable.
  • Ingestion points: User responses to interview questions and outputs from linked skills in the samber/dev-event-organizer-skills collection.
  • Boundary markers: The skill instructions do not specify explicit delimiters for external data.
  • Capability inventory: The skill is limited to generating text-based marketing plans and delegating tasks to other modular skills.
  • Sanitization: No explicit sanitization of user or sibling data is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 09:13 PM
Security Audit — agent-trust-hub — event-marketing-plan