event-social-media

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions and referenced documentation focus entirely on strategic planning, content scheduling, and community management for technical events. No evidence of prompt injection, data exfiltration, or unauthorized command execution was found.
  • [SAFE]: External references to organizations like CNCF (Cloud Native Computing Foundation), Major League Hacking (MLH), and DevOpsDays are used as sources for best practices and governance guidelines.
  • [SAFE]: The skill uses a vendor-specific referencing format (samber/dev-event-organizer-skills@...) to coordinate with related skills from the same author, which is consistent with the stated development ecosystem.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data via user interviews (e.g., audience locations, existing handles, sponsor names). However, the skill has no dangerous capabilities (like file writing, network requests, or code execution) that could be exploited through this data ingestion, and it primarily generates static text plans and templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 09:13 PM
Security Audit — agent-trust-hub — event-social-media