skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/open-data-integrator/Gen Agent Trust Hub
open-data-integrator
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data (CSV, Excel, JSON) provided by the user, which could contain hidden malicious instructions.
- Ingestion points: As noted in
instructions.md, the agent accepts project data, file paths, and parameters directly from the user to perform enrichment and analysis. - Boundary markers: There are no explicit boundary markers or system-level instructions provided to the agent to treat ingested data as data only and ignore any embedded natural language instructions.
- Capability inventory: The skill implementation in
SKILL.mdincludes network capabilities via therequestslibrary, andclaw.jsonrequests bothnetworkandfilesystempermissions. - Sanitization: No sanitization or validation logic is present to filter or escape instructions that might be embedded within the project datasets or parameters before they are processed by the LLM.
Audit Metadata