linkfox-jiimore-page-asins-by-asin
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATIONPERSISTENCECOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and displays data from external Amazon product listings, which could be exploited for indirect prompt injection if the content contains malicious instructions.
- Ingestion points: Product titles, niche descriptions, and brand names are fetched from the vendor API and processed in
scripts/jiimore_page_asins_by_asin.py. - Boundary markers: There are no explicit instructions or delimiters defined to isolate the external content or instruct the agent to ignore embedded commands.
- Capability inventory: The skill possesses network access to interact with APIs and file system write capabilities for logging results.
- Sanitization: The skill does not implement explicit sanitization or validation of the fetched product data before presenting it to the agent.
- [DATA_EXFILTRATION]: The onboarding script (
scripts/onboarding.py) collects and transmits user PII, specifically phone numbers and SMS verification codes, to vendor authentication servers (api.linkfox.com). - [PERSISTENCE]: The skill provides explicit instructions to users to store API keys in shell configuration files (
.bashrc,.zshrc) and environment variables to maintain session persistence. - [COMMAND_EXECUTION]: The skill executes local Python scripts to facilitate API communication and manage user account onboarding tasks.
Audit Metadata