linkfox-temu-add-product-us
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFECREDENTIALS_UNSAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill manages sensitive Temu API tokens by persisting them in a local JSON file at
~/.linkfox/temu-access-tokens.json. While this is standard for maintaining session state across tool executions, it creates a local sensitive data footprint. - [DATA_EXPOSURE_AND_EXFILTRATION]: The
scripts/onboarding.pyutility facilitates user authentication by collecting phone numbers and verification codes, which are transmitted to the vendor's authentication services (api.linkfox.comandagent-api.linkfox.com). This is the intended purpose of the onboarding script provided by the vendor. - [UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill performs network operations to interact with various vendor-owned domains, including
tool-gateway.linkfox.comfor API proxying andskill-api.linkfox.comfor feedback. These operations are essential for the skill's functionality and target the author's own infrastructure. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources (Temu Product APIs) which is then presented to the agent.
- Ingestion points: Data enters the context via the
call_temu_apifunction inscripts/_temu_common.pywhen retrieving product lists, details, or category information. - Boundary markers: There are no specific delimiters or instructions to the agent to ignore potentially malicious instructions embedded in the Temu API responses.
- Capability inventory: The skill has the ability to write to the local filesystem (within the
linkfox/directory) and perform further network requests via the gateway scripts. - Sanitization: The scripts parse the JSON responses from Temu but do not apply specific sanitization or filtering to the text content before it reaches the agent context.
Audit Metadata