skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/data-evolution-analysis/Gen Agent Trust Hub
data-evolution-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data formats such as CSV, Excel, and JSON provided by the user to perform digital maturity assessments. This creates an indirect prompt injection surface where malicious instructions could theoretically be embedded in the data. However, the risk is limited as the skill lacks high-risk capabilities like network access or arbitrary command execution.
- Ingestion points: Project data and survey responses provided by users in various formats (instructions.md).
- Boundary markers: The instructions do not specify explicit delimiters or 'ignore' commands for the processed data content.
- Capability inventory: The skill is granted filesystem permissions for reading and writing reports but does not have access to network tools or dynamic execution environments.
- Sanitization: No specific content sanitization or input validation logic is implemented in the provided Python classes.
Audit Metadata