skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/kpi-dashboard/Gen Agent Trust Hub
kpi-dashboard
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core functionality of ingesting and processing untrusted project data from external files.
- Ingestion points: The 'instructions.md' file indicates that the agent accepts data from user-provided file paths or direct inputs in CSV, Excel, and JSON formats.
- Boundary markers: The skill does not implement delimiters or 'ignore' instructions to prevent the model from obeying commands embedded within the data.
- Capability inventory: The skill possesses 'filesystem' permissions and has the capability to write files to the disk using the 'export_to_excel' method.
- Sanitization: There is no evidence of sanitization or validation of external content before it is processed or used to generate HTML and Excel reports.
Audit Metadata