crisis-risk-monitor

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [DATA_EXFILTRATION]: The skill reads environment definitions and configuration files to discover system architecture. While intended for auditing, this involves accessing sensitive file paths.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the analysis of untrusted codebase content. Ingestion points: Reads codebase files, clinical notes, and configuration manifests from the local environment. Boundary markers: Absent; instructions do not provide delimiters for untrusted data. Capability inventory: Investigative agent with broad file-reading and analysis capabilities. Sanitization: Absent; the skill does not validate or sanitize content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 10:56 AM
Security Audit — agent-trust-hub — crisis-risk-monitor