affiliate-program-search
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources, creating a potential surface for indirect prompt injection if the source content is maliciously crafted.
- Ingestion Points: Data is ingested from the openaffiliate.dev API (GET /api/programs) and through web searches for product reviews and market trends using the web_search and web_fetch tools.
- Boundary Markers: The skill instructions specify a structured output schema for internal data handling but do not define explicit delimiters or instructions to ignore embedded commands within the fetched external content.
- Capability Inventory: The skill's capabilities are limited to network operations (HTTP GET, web search, web fetch) and data processing. It does not have access to the local file system (beyond its own reference files), shell execution, or credential storage.
- Sanitization: No explicit sanitization or filtering of external API or web content is described prior to its use in the scoring and recommendation workflow.
Audit Metadata