healthcare-clinical-triage

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script located at /sandbox/.openclaw/workspace/scripts/care_backlog_analyzer.py to perform triage logic based on synthetic data.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data files, creating a surface for potential indirect instructions.
  • Ingestion points: Reads data from referrals.csv, escalation_rules.json, and clinical_notes.json located in /sandbox/.openclaw/workspace/data/ as specified in SKILL.md.
  • Boundary markers: Absent; the instructions do not specify delimiters or warnings for the agent to ignore instructions embedded within the clinical notes or referral data.
  • Capability inventory: Executes a subprocess command via python3 to run the analyzer script.
  • Sanitization: Absent; no explicit validation or filtering of the input data is mentioned in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 08:28 AM
Security Audit — agent-trust-hub — healthcare-clinical-triage