gdpr-dsgvo-expert

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute local shell commands to run Python scripts (gdpr_compliance_checker.py, dpia_generator.py, and data_subject_rights_tracker.py) for auditing code and tracking data subject requests.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it processes untrusted data from external project directories.
  • Ingestion points: Source code and project files scanned by the gdpr_compliance_checker.py script.
  • Boundary markers: No explicit delimiters or delimiters for untrusted content are defined in the skill documentation to prevent the agent from obeying instructions embedded in scanned files.
  • Capability inventory: The skill allows for shell command execution and local file system read/write operations through its script-based tools.
  • Sanitization: The documentation does not outline any sanitization or validation processes for the data extracted from scanned codebases before it is processed by the AI.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 08:06 PM
Security Audit — agent-trust-hub — gdpr-dsgvo-expert