agency-china-market-localization-strategist
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill is composed of high-quality instructional prompts for marketing and localization strategy with no executable code or remote dependencies.- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that ingests and analyzes external trend data from various Chinese social media platforms, creating a theoretical attack surface for indirect prompt injection. 1. Ingestion points: External hotlist and trend data from platforms like Douyin, Bilibili, and Weibo (SKILL.md). 2. Boundary markers: No specific delimiters or instructions to ignore embedded commands are provided. 3. Capability inventory: The skill code itself lacks subprocess calls, network operations, or file-writing capabilities. 4. Sanitization: No sanitization or filtering of external content is described. Given the purely instructional nature of the skill and the absence of high-risk capabilities, this surface is considered safe.
Audit Metadata