1688-marketing-skill
Warn
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions direct users to clone a repository from
https://github.com/next-1688/1688-marketing.gitand install dependencies. This source is not associated with the skill author 'Aradotso' or any established trusted organizations, posing a risk of executing unverified external code. - [PROMPT_INJECTION]: The skill is designed to ingest and process marketing data, activity descriptions, and pricing information from the 1688 platform API. This data is untrusted and could contain malicious instructions designed to influence the agent's behavior (Indirect Prompt Injection).
- Ingestion points: Data retrieved via
ActivityQueryClient.query_activities,PricingClient.get_suggested_price, andOpportunityClient.get_recommendations(SKILL.md). - Boundary markers: The instructions do not define clear delimiters or warnings to the agent to ignore instructions embedded within the API data.
- Capability inventory: The skill has the capability to perform API-driven actions such as submitting registrations (
submit_enrollment) and applying dynamic pricing strategies. - Sanitization: There is no evidence of sanitization or validation of the content retrieved from the platform before it is utilized in the logic flow.
Audit Metadata