stat-causal-inference
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze observational data provided by the user. This establishes a surface for indirect prompt injection where instructions could be embedded in the data fields to influence the agent's behavior.
- Ingestion points: External datasets described in SKILL.md and examples/sample_scenario.md.
- Capability inventory: The agent uses data analysis tools to read, manipulate, and model this data.
- Sanitization: The skill emphasizes checking statistical assumptions but does not specify input sanitization for the agent's logic.
- [DYNAMIC_EXECUTION]: The skill includes numerous Python and R code templates for generating causal models and graphs. The agent is expected to generate and execute this code to fulfill analysis requests.
- Evidence: Code snippets using networkx, pgmpy, statsmodels, and linearmodels in the references directory.
- Execution method: Standard script generation from known templates for functional data analysis.
Audit Metadata