linkfox-geekbi-temu-market-research
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPERSISTENCEINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill performs network operations targeting
tool-gateway.linkfox.com,api.linkfox.com,agent-api.linkfox.com, andskill-api.linkfox.com. These requests are used to retrieve Temu market research data, facilitate user authentication, manage account billing, and submit operational feedback. - [COMMAND_EXECUTION]: The skill uses Python scripts to wrap API calls, handle session-based logging in the local
linkfox/directory, and manage a local cache of research results. It also uses a script to generate QR codes for user payments during the onboarding process. - [PERSISTENCE]: The skill's onboarding documentation (
references/onboarding.md) instructs users on how to manually persist theirLINKFOX_AGENT_API_KEYby adding it to shell configuration files such as.bashrcand.zshrc, or by using the Windowssetxcommand. This is a standard method for managing persistent environment variables for API authentication. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data from the Temu marketplace, creating a potential surface for indirect prompt injection if that data contains malicious instructions.
- Ingestion points: Marketplace data is ingested from the
tool-gateway.linkfox.comAPI via search scripts. - Boundary markers: The skill body provides structured formatting for results but does not define explicit delimiters to isolate external data from the agent's system instructions.
- Capability inventory: The skill has the ability to write to the local filesystem (logging/caching) and perform network requests to vendor APIs.
- Sanitization: Results are processed as JSON, but there is no evidence of additional sanitization applied to the content before it is presented to the agent or user.
Audit Metadata