skills/sanool/healthskills/mood/Gen Agent Trust Hub

mood

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [Command Execution] (LOW): The skill instructs the agent to use the Bash open command to launch URLs. While the provided URLs point to reputable services like Spotify and YouTube, the use of system commands to interact with external resources is a practice that requires caution.
  • [Indirect Prompt Injection] (LOW): The skill is designed to monitor and process untrusted user input (emotional distress signals) which serves as an attack surface for indirect prompt injection.
  • Ingestion points: User chat messages containing frustration, anxiety, or specific phrases (e.g., "this stupid code", "I quit").
  • Boundary markers: Absent. The skill does not provide delimiters or instructions for the agent to ignore potentially malicious content embedded within the user's emotional venting.
  • Capability inventory: Execution of the Bash open command to trigger external browser activity.
  • Sanitization: Absent. No validation or escaping is applied to the content identified as emotional distress before the agent acts upon it.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:37 PM