skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/cwicr-multilingual/Gen Agent Trust Hub
cwicr-multilingual
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests construction work item data from external files using the
load_databasemethod inSKILL.md. Malicious instructions hidden within these data files could potentially influence agent behavior when the content is processed or displayed. - Ingestion points: External data is loaded from local CSV, Excel, and Parquet files into pandas DataFrames as implemented in
SKILL.md. - Boundary markers: The skill does not employ delimiters or explicit instructions to the agent to ignore potentially malicious content within the database fields.
- Capability inventory: The skill is capable of reading files from the local filesystem as permitted by the
filesystempermission inclaw.json. - Sanitization: There is no evidence of sanitization, filtering, or validation of the text content (e.g., item descriptions) retrieved from the source files.
Audit Metadata