amz-backend-keywords
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input in the form of Amazon product listings (titles and bullet points) and keyword lists. * Ingestion points: Title, bullets, and keyword lists provided by the user as described in the 'Step by step' section of SKILL.md. * Boundary markers: None present to delimit user input from instructions or to prevent the agent from obeying instructions embedded in the data. * Capability inventory: The skill uses no external tools, shell commands, or file system access, limiting the risk of exploitation. * Sanitization: No sanitization of user-provided content is performed before processing.
Audit Metadata