data-cleaning
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external datasets, creating a surface for potential indirect prompt injection if the data contains malicious instructions intended for the agent.
- Ingestion points: Raw datasets are loaded from file paths using
pandas.read_csvas described inSKILL.md. - Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions within the dataset content.
- Capability inventory: Capabilities are limited to data manipulation and local file writes (
df.to_csv) in the provided examples, with no network access or arbitrary command execution enabled. - Sanitization: The skill enforces data types and schemas, which provides basic structural validation but does not filter for language-based injection attacks.
Audit Metadata