linkfox-shopify-store-query
Warn
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: MEDIUMCREDENTIALS_UNSAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PERSISTENCE_MECHANISMS]: The skill provides instructions and automation in
references/onboarding.mdandscripts/onboarding.pyto modify shell configuration files such as~/.zshrcand~/.bashrc. This is used to persist theLINKFOX_AGENT_API_KEYenvironment variable across user sessions to maintain access to the service. - [DATA_EXPOSURE_AND_EXFILTRATION]: The
onboarding.pyscript retrieves the user's API Key from the LinkFox backend and prints it in plaintext to the standard output during the setup process. Additionally, the script contains a hardcoded base64-encoded identifier (_LOGIN_FIXED_UID) used in authentication headers for login requests. - [UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill relies on the execution of local Python scripts to perform account management and query external Shopify data. These scripts rely on external packages (
requests,qrcode,pillow) and perform network operations to vendor-specific domains to transmit credentials and fetch store data. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted store metadata, including store names, domains, and social descriptions, from
tool-gateway.linkfox.com. This data is presented to the agent context without sanitization, creating a potential surface for indirect prompt injection. - Ingestion points: External API responses from Shopify queries processed within
scripts/shopify_store_query.py. - Boundary markers: No specific delimiters or instructions to ignore embedded content are present in the prompt templates.
- Capability inventory: The skill has access to network tools (via
urllibandrequests) and local file system write access for session logging. - Sanitization: No escaping, validation, or filtering of the fetched store data is performed before it is rendered for the agent's consumption.
Audit Metadata