data-cleaner
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process messy datasets, which serves as an ingestion point for untrusted data that could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: User-provided datasets (CSV, JSON, etc.) described in the skill's purpose in
SKILL.md. - Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" markers for the data being cleaned.
- Capability inventory: The skill utilizes Python and Pandas to perform data transformations and analysis.
- Sanitization: There are no explicit sanitization steps mentioned to filter out natural language instructions embedded within the data values.
Audit Metadata