alterlab-tr-research-ethics

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill scaffolds Turkish 'etik kurul' (ethics committee) applications using local templates and routing rules based on official TR Dizin/ULAKBİM and TİTCK regulations. All operations are local and static.
  • [SAFE]: The included Python script scripts/consent_form_check.py is a simple linter that uses only the Python standard library. It performs basic keyword matching to ensure required elements are present in consent form drafts. It does not use eval(), exec(), or any network-based functions.
  • [SAFE]: Data processing is limited to reading user-provided draft files for the purpose of checking them against a checklist. There is no evidence of indirect prompt injection or capability for data exfiltration.
  • [SAFE]: External references are restricted to official Turkish government domains (e.g., titck.gov.tr, mevzuat.gov.tr) and academic repositories (trdizin.gov.tr). No suspicious or obfuscated URLs were detected.
  • [SAFE]: The skill explicitly boundaries its scope, deferring data management plan tasks to sibling skills (alterlab-kvkk-dmp) and international ethics to others (alterlab-research-ethics), showing a clear and safe architectural design.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 02:36 PM