kuaishou-sentiment-dashboard
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external content from Kuaishou links provided by the user, creating a potential surface for indirect prompt injection if the external data contains malicious instructions designed to influence the agent.
- Ingestion points: The
videoUrlparameter defined inreferences/form-schema.jsonand utilized inSKILL.md. - Boundary markers: None present in the skill instructions to delimit the untrusted external content.
- Capability inventory: The skill utilizes
scripts/run.pyto perform network operations and poll API endpoints. - Sanitization: No explicit sanitization or filtering of the retrieved content is performed within the local scripts.
- [COMMAND_EXECUTION]: The skill includes a local Python script (
scripts/run.py) that the agent is instructed to execute to perform data processing, link parsing, and API task management. - [EXTERNAL_DOWNLOADS]: The skill performs network requests to the external domain
ai-skills.ai(the vendor's infrastructure) to parse video links and retrieve sentiment analysis results.
Audit Metadata