compliance-auditor

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands (grep) and internal Python scripts (e.g., scripts/check_gdpr.py, scripts/validate_hipaa.py) to perform compliance checks and evidence collection from the local environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an inherent vulnerability to indirect prompt injection as it is designed to analyze untrusted external data.
  • Ingestion points: The agent analyzes user-provided files including JSON, YAML, and Markdown within the config/, policies/, and procedures/ directories (in SKILL.md).
  • Boundary markers: There are no explicit instructions to the agent to treat data from these files as untrusted or to ignore any potential embedded instructions.
  • Capability inventory: The skill enables the agent to execute shell commands and internal Python scripts based on the analysis of these files (in SKILL.md).
  • Sanitization: The skill does not describe or implement any sanitization or validation of the content processed from external files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 08:05 AM
Security Audit — agent-trust-hub — compliance-auditor