skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/data-profiler/Gen Agent Trust Hub
data-profiler
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill implementation follows secure coding practices for data profiling. No instances of obfuscation, hardcoded credentials, or suspicious network activities were identified.
- [INDIRECT_PROMPT_INJECTION]: The skill has a potential attack surface due to its core function of processing external datasets provided by users.
- Ingestion points: The skill ingests data from CSV, Excel, and JSON files as described in the SKILL.md implementation and instructions.md.
- Boundary markers: No explicit delimiters are employed to separate data values from potential instructions during processing.
- Capability inventory: The skill utilizes filesystem access and local Python execution for its data analysis tasks.
- Sanitization: Input validation is focused on data structure and construction patterns via regular expressions, but no specific logic is present to sanitize for prompt injection.
- [EXTERNAL_DOWNLOADS]: The documentation references standard, well-known Python packages (pandas, numpy) from official registries.
Audit Metadata