gdpr-breach-72h-en

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill utilizes the Bash tool to execute a local Python script (scripts/gdpr_deadlines.py). This script is a clerical aid for calculating date-based deadlines (72 hours for breaches, 1-3 months for DSARs). A review of the source code confirms it uses only Python standard libraries, lacks network or disk-write capabilities, and operates only on user-provided timestamps.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied incident details, creating an ingestion surface for potentially malicious instructions.
  • Ingestion points: User-provided breach descriptions and awareness timestamps (SKILL.md).
  • Boundary markers: None explicitly defined in the instructions to separate data from instructions.
  • Capability inventory: The skill has access to Bash (for the local deadline script) and Read tools.
  • Sanitization: No input sanitization is performed by the skill instructions.
  • Risk Assessment: The risk is addressed by the explicit requirement for human approval of all drafts and the limited, non-networked capabilities of the provided tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 11:09 AM
Security Audit — agent-trust-hub — gdpr-breach-72h-en