scanning-for-gdpr-compliance

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes external data files, creating a surface for indirect prompt injection.
  • Ingestion points: The Python scripts scripts/gdpr_scan.sh and scripts/report_generator.py process files and directories from the input paths provided by the user.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the script logic to protect the agent from malicious content within scanned files.
  • Capability inventory: The skill is granted broad permissions including Bash(security:*), Bash(scan:*), and Bash(audit:*), alongside file read/write access.
  • Sanitization: There is no evidence of content sanitization or validation of the files' text before it is processed by the agent.
  • [COMMAND_EXECUTION]: The SKILL.md metadata allows broad Bash tool access using wildcards (e.g., Bash(security:*)), which provides more permissions than may be strictly necessary for the scanning tasks and increases the potential impact of a prompt injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 08:31 PM