rodo-naruszenie-72h-pl

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute a local utility script scripts/gdpr_deadlines.py. This script is used for deterministic calculations of legal deadlines based on user input.\n
  • Evidence: python scripts/gdpr_deadlines.py breach --from "2026-06-30T14:30" in SKILL.md.\n
  • Logic: The script uses standard Python libraries, performs no file system writes, and has no network dependencies.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied incident descriptions to categorize breaches and assess risks, which represents a potential attack surface for indirect prompt injection.\n
  • Ingestion points: The skill body indicates that an incident description provided by the user is passed to the model for analysis.\n
  • Boundary markers: Absent. The skill does not define specific delimiters or instructions to ignore embedded commands within the incident description.\n
  • Capability inventory: The agent has access to Bash (for execution of the local deadline script) and Read tools.\n
  • Sanitization: Absent. The skill relies on the underlying model's safety filters for processing input content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 07:31 PM
Security Audit — agent-trust-hub — rodo-naruszenie-72h-pl