kuaishou-scraper-api
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill performs network operations to
api.scavio.devandscavio.devto interact with the vendor's data scraping services. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the Kuaishou platform, including user profiles, video comments, and search results, which could contain instructions intended to influence the agent's behavior.
- Ingestion points: Data retrieved from Kuaishou via the
api.scavio.devendpoints (SKILL.md). - Boundary markers: The instructions do not define specific delimiters to isolate untrusted data from the agent's system prompt.
- Capability inventory: No file system writes or subprocess executions are defined in the provided file, though the skill relies on the agent's networking capabilities.
- Sanitization: There is no mention of sanitizing or escaping the content retrieved from the social media platform before presenting it to the agent context.
Audit Metadata