find-orders
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted content from external Amazon order pages (such as product titles or seller information).
- Ingestion points: The skill instructions in
references/order-workflow.mdspecify reading Amazon order history and detail pages. - Boundary markers: There are no explicit instructions or delimiters to wrap or sanitize content retrieved from Amazon to prevent the agent from following instructions embedded in that content.
- Capability inventory: The skill summarizes and processes data from the browser to present findings to the user (
SKILL.md). - Sanitization: No sanitization or validation of the text content retrieved from the web pages is performed before it is processed by the AI.
Audit Metadata