linkfox-echotik-batch-product-detail
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted product metadata retrieved from TikTok via the EchoTik API, which the agent is then instructed to summarize.
- Ingestion points: Data fields such as
productNameanddescDetailfetched by the/echotik/batchProductDetailAPI inscripts/echotik_batch_product_detail.py. - Boundary markers: There are no explicit delimiters or safety instructions (e.g., "ignore embedded instructions") provided in the skill body for handling these external data fields.
- Capability inventory: The skill possesses file system write access to the
linkfox/directory and is capable of local script execution viasubprocess.run. - Sanitization: No explicit sanitization or filtering of the ingested product data is performed before it is processed by the agent.
- [DYNAMIC_EXECUTION]: The utility script
scripts/response_io.pyusessubprocess.runto execute other Python scripts within the skill's directory using user-supplied parameters. This mechanism is used for managing large API responses but represents a dynamic execution pattern where the execution path is computed at runtime.
Audit Metadata