data-analysis
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes external datasets without explicit security boundaries.
- Ingestion points: The 'Instructions' section in SKILL.md specifies that users provide dataset paths or raw CSV/JSON content.
- Boundary markers: There are no defined delimiters or instructions to the agent to ignore potentially malicious commands embedded within the data records.
- Capability inventory: The skill leverages high-capability libraries like 'pandas', 'scikit-learn', and 'matplotlib', which often involve the generation and execution of Python code to perform analysis.
- Sanitization: While the skill performs 'Data Quality Checks' for missing values and outliers, it does not implement sanitization or filtering for instructional text hidden within data fields.
Audit Metadata