skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/erp-integration-analysis/Gen Agent Trust Hub
erp-integration-analysis
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 user-provided construction project data in formats like CSV, Excel, and JSON, as specified in
instructions.md. This creates a theoretical surface where malicious instructions could be embedded within the data files processed by the agent. - Ingestion points: Project data, file paths, and parameters provided by the user (found in
instructions.md). - Boundary markers: The skill does not explicitly define delimiters or instructions to ignore embedded commands within the processed data.
- Capability inventory: The skill includes extensive Python logic in
SKILL.mdfor analyzing system integration, mapping flows, and generating reports. - Sanitization: There is no evidence of specific sanitization or filtering of the content within the ingested data files to prevent prompt injection.
Audit Metadata