saks-fifth-avenue-api
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted product data such as titles and descriptions retrieved from saksfifthavenue.com.
- Ingestion points: Data entering through
/saks/search,/saks/product, and/saks/suggestionsendpoints documented in SKILL.md. - Boundary markers: No explicit delimiters or instruction-ignore blocks are defined in the provided documentation to separate untrusted product data from agent instructions.
- Capability inventory: The skill documentation describes network-based API querying tools; it does not grant permissions for local file system modification, shell command execution, or other high-privilege operations to the agent.
- Sanitization: No sanitization or validation logic for the external product content is documented.
Audit Metadata