code-data-analysis-scaffolds
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- PROMPT_INJECTION (LOW): Vulnerable to Indirect Prompt Injection (Category 8).
- Ingestion points: User-provided datasets or codebases as described in
SKILL.md(Step 1) and triggered by phrases like 'Explore this dataset'. - Boundary markers: Absent; the instructions do not include specific delimiters or warnings to ignore instructions embedded in the processed data.
- Capability inventory: The skill involves generating and executing code using libraries such as
pandasandpytest, as seen inSKILL.md(Step 5) and the examples. - Sanitization: Absent; no escaping or validation of external content is specified before interpolation into agent actions.
Audit Metadata