gdpr-doc-review
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill methodology and the Python processing script (
scripts/process.py) are focused on local auditing tasks. The script uses standard libraries for math and JSON parsing without network or dangerous system access. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external documentation (e.g., privacy notices, contracts, RoPA), which constitutes a potential ingestion surface for indirect prompt injection.
- Ingestion points: Methodology in
SKILL.mdandreferences/workflows.mdinvolving the review of third-party documentation. - Boundary markers: None identified in the provided instructions.
- Capability inventory: Limited to the
process.pyscript for scoring and standard agent text processing; no network or high-privilege tool usage detected. - Sanitization: No specific content sanitization logic is prescribed for the analyzed documents.
Audit Metadata