supplier-selection
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to handle external supplier data, such as RFP responses and evaluation criteria, creating a potential surface for indirect prompt injection.\n
- Ingestion points: Data dictionaries passed to functions like
weighted_scoring,assess_financial_health, and theadd_supplier_responsemethod in theRFPScorerclass.\n - Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands embedded within supplier text.\n
- Capability inventory: The skill is restricted to data analysis using
pandasandnumpy. No dangerous capabilities like shell execution, file system writes, or network access are included in the code.\n - Sanitization: The provided Python snippets do not include input validation or sanitization for string-based metadata.
Audit Metadata