pandera-validation
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from external DataFrames, creating a surface for indirect prompt injection attacks where data content could influence the agent's behavior.
- Ingestion points: The
validate_with_errorsandinfer_and_export_schemafunctions inscripts/schemas.pytakepd.DataFrameobjects as input, which are often loaded from external files or APIs. - Boundary markers: There are no explicit delimiters or specific instructions for the agent to ignore natural language instructions embedded within the DataFrame content.
- Capability inventory: The skill is granted access to the
Bashtool inSKILL.md, which could be exploited if an injection leads the agent to execute shell commands. - Sanitization: The skill performs structural and type-level validation via Pandera but does not include sanitization or filtering for potential prompt injection strings within string-based columns.
Audit Metadata