kuaishou-profile-scraper
Warn
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: MEDIUMPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The instructions attempt to override agent safety protocols by directing the agent to install dependencies "automatically without asking the user to confirm" and explicitly forbidding the agent from requesting "separate approval for dependency installation."
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface:
- Ingestion point: Processes external Kuaishou profile data (SKILL.md).
- Boundary markers: None present to delimit or ignore instructions within scraped data.
- Capability inventory: Invokes external CLI tool browser-act which can perform network and file operations.
- Sanitization: No evidence of data sanitization or validation before processing.
- [EXTERNAL_DOWNLOADS]: The skill mandates the installation of an external CLI tool (BrowserAct) from an untrusted third-party source via a redirecting URL.
- [COMMAND_EXECUTION]: The skill's workflow depends on executing the browser-act CLI, which is a binary or script acquired from an external source at runtime.
Audit Metadata