bilibili-creator-scraper
Fail
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: HIGHPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The instructions contain an explicit command to override safety protocols, telling the agent to "install the missing dependency automatically without asking the user to confirm" and to "not request separate approval for dependency installation."
- [EXTERNAL_DOWNLOADS]: The skill requires a CLI tool from a third-party domain (
www.browseract.com) that is not identified as a trusted vendor or well-known service, creating a supply chain risk through unverified external code ingestion. - [COMMAND_EXECUTION]: The skill depends on the execution of the
browser-actCLI, which it attempts to install and run autonomously without user oversight. - [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes data from external Bilibili pages and uses it as input for CLI commands without evidence of sanitization or boundary markers.
- Ingestion points: Bilibili creator URLs and content pages.
- Boundary markers: None; lacks delimiters or instructions to ignore embedded commands in the processed data.
- Capability inventory: Execution of the
browser-actCLI with parameters derived from external content. - Sanitization: None; the skill does not specify any validation or escaping of scraped web content before processing.
Recommendations
- AI detected serious security threats
Audit Metadata