skills/simota/agent-skills/cloak/Gen Agent Trust Hub

cloak

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a technical advisor for privacy audits and regulatory compliance, offering detailed guidance and implementation patterns.
  • [EXTERNAL_DOWNLOADS]: Reference files include code templates for consent management that mention well-known services such as Google Tag Manager and Facebook Pixels. These are provided as implementation examples for the user rather than being executed by the agent.
  • [DATA_EXFILTRATION]: No patterns of unauthorized data exfiltration were found. The skill contains explicit instructions to redact sensitive information and sanitize data before it is processed by an LLM.
  • [CREDENTIALS_UNSAFE]: No hardcoded credentials, API keys, or secrets were detected. Examples provided use standard placeholders and emphasize secure secret management.
  • [PROMPT_INJECTION]: While the skill's primary function involves scanning external codebases (creating an indirect prompt injection surface), the internal instructions prioritize strict data classification, regulatory adherence, and recall-driven auditing to maintain a safe operational environment.
  • [NO_CODE]: The skill consists of markdown instructions and reference documentation without shipping executable scripts or binaries.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 01:01 AM
Security Audit — agent-trust-hub — cloak