amazon-sp-sqp-asin-ngram
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze external Amazon search query data, which represents a potential surface for indirect prompt injection attacks.
- Ingestion points: External data enters the agent context via the
search_queryandasin_metricsfields described in theDecision objectschema inSKILL.md. - Boundary markers: The skill uses structured JSON to organize input data but does not explicitly instruct the agent to ignore or delimit instructions that might be embedded within the
search_querytext. - Capability inventory: The skill documentation and reference files do not define any high-risk capabilities such as network operations, file system modifications, or subprocess execution.
- Sanitization: No specific input sanitization or validation logic is defined to filter malicious instructions from the incoming data streams.
Audit Metadata