ic-events

Pass

Audited by Gen Agent Trust Hub on Jul 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions and installation scripts fetch content from https://www.immersivecommons.com/skills/ic-events/SKILL.md. These downloads target the official vendor domain and are used for skill installation.
  • [COMMAND_EXECUTION]: The skill uses curl commands to interact with the Immersive Commons API at https://www.immersivecommons.com/api/events/. These operations are required for the skill's primary functionality (listing events and submitting RSVPs) and target official endpoints.
  • [DATA_EXFILTRATION]: The skill handles an agent token (FLOOR10_AGENT_TOKEN) and user email addresses. These are transmitted only to the official immersivecommons.com API endpoints over HTTPS. The skill explicitly instructs the agent to ask the human for the email and confirmation before RSVPing, preventing unauthorized data usage.
  • [PROMPT_INJECTION]: No evidence of prompt injection, bypass instructions, or safety override attempts were found in the skill content.
  • [CREDENTIALS_UNSAFE]: The skill uses an environment variable (FLOOR10_AGENT_TOKEN) for authentication, which is a standard and safe practice for managing secrets in agent environments. No hardcoded credentials were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 19, 2026, 10:20 PM
Security Audit — agent-trust-hub — ic-events