grand-slam-offer
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources and user input without explicit safety boundaries.
- Ingestion points: The skill uses
web_searchto research product features and pricing in 'Step 1: Gather Context'. It also accepts user-provided strings for the product description and reward values. - Boundary markers: The instructions lack explicit delimiters or instructions to the agent to treat the retrieved search data as non-executable text.
- Capability inventory: The skill is scoped to information gathering and text generation; it utilizes
web_searchand reads local reference files (shared/references/offer-frameworks.md). It does not have access to sensitive system files or arbitrary code execution. - Sanitization: There is no evidence of validation or sanitization for the content returned by external search queries before it is used to influence the final offer copy.
Audit Metadata