skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/enterprise-risk-aggregator/Gen Agent Trust Hub
enterprise-risk-aggregator
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill implements risk aggregation logic using standard Python libraries and follows best practices for data modeling. No malicious code, network operations, or unauthorized data access patterns were identified.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface through the processing of external data formats such as CSV, Excel, and JSON.
- Ingestion points: The skill accepts project data from user-provided files (CSV, Excel, JSON) or direct input as described in instructions.md.
- Boundary markers: No specific delimiters or boundary markers are defined to isolate untrusted data from the agent's instructions.
- Capability inventory: The core implementation is limited to statistical analysis and does not involve subprocess execution, network requests, or file-writing operations.
- Sanitization: No specific input sanitization or validation logic is implemented for the processed data fields.
Audit Metadata