healthcare-command-summary
Pass
Audited by Gen Agent Trust Hub on Jul 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Executes local Python scripts located at
/sandbox/.openclaw/workspace/scripts/care_backlog_analyzer.pyto generate reports and summaries based on operational data. - [PROMPT_INJECTION]: The skill ingests and processes various evidence sources, creating a potential surface for indirect prompt injection attacks.
- Ingestion points: Data entering the context from intake, triage, capacity, and audit evidence sources.
- Boundary markers: Absent; the skill does not use specific delimiters or instructions to the agent to ignore instructions within the source data.
- Capability inventory: The skill possesses the capability to execute shell commands via Python scripts in the sandbox environment.
- Sanitization: No sanitization, filtering, or validation processes for the input evidence data are mentioned in the skill instructions.
Audit Metadata