skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/labor-allocation/Gen Agent Trust Hub
labor-allocation
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes external data formats (CSV, Excel, JSON) which introduces a surface for indirect prompt injection.
- Ingestion points:
instructions.mdspecifies that the agent accepts data in common file formats for processing. - Boundary markers: No delimiters or protective instructions are used to distinguish data from potential embedded commands.
- Capability inventory: The skill includes methods for filesystem writes via
export_to_exceland holds thefilesystempermission. - Sanitization: No explicit validation or cleaning of the input data is performed before processing.
- [SAFE]: All logic in
SKILL.mdis focused on resource allocation, cost calculation, and reporting, with no signs of obfuscation or malicious behavior. - [SAFE]: The skill uses well-known, trusted Python libraries (pandas, openpyxl) and references the author's own official domain (datadrivenconstruction.io).
Audit Metadata