ramp-core-workflow-b
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from the Ramp API (transactions, merchant names, and cardholder info) which could contain malicious instructions if the source is compromised.
- Ingestion points: Fetches external transaction data using
requests.getinSKILL.md. - Boundary markers: No specific delimiters or warnings are used when processing the transaction data.
- Capability inventory: Includes network operations via the Python
requestslibrary and tool access forBash(curl:*)andBash(npm:*)in the YAML frontmatter. - Sanitization: The skill does not perform sanitization or validation on the fields returned by the API before processing or displaying them.
Audit Metadata