ropa-tool-integration
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external JSON and CSV files, creating a surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: RoPA data is ingested through
load_ropa_jsonandimport_from_csvinscripts/process.py. - Boundary markers: No specific delimiters or instructions are used to separate ingested data from agent commands.
- Capability inventory: The skill includes file system write operations in
scripts/process.pyand network API requests described inSKILL.md. - Sanitization: Output formatting relies on standard
jsonandcsvlibraries which provide structural escaping but no semantic sanitization of the data fields. - [SAFE]: The skill demonstrates secure development practices by referencing environment variables for API secrets rather than hardcoding credentials.
- [SAFE]: All network activity and API configurations are directed toward well-known enterprise privacy platforms (OneTrust, TrustArc, Collibra, DataGrail) as expected for the skill's functionality.
Audit Metadata