bilibili-creator-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The skill instructs the agent to automatically install dependencies and explicitly tells it not to request or disclose user approval (hide the installation request), which is a deceptive operational instruction outside the stated scraping purpose.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). SKILL.md instructs the agent to use BrowserAct to access real Bilibili web pages at runtime (public web content authored by outsiders), which can be ingested as readable page text into the LLM context via the BrowserAct workflow.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill requires and instructs the agent to automatically install the BrowserAct CLI at runtime using the provided installer URLs (https://www.browseract.com/?co-from=social-media and https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main), which implies fetching and executing remote code as a required dependency.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (medium risk: 0.60). The Skill explicitly instructs the agent to install the BrowserAct CLI automatically without asking the user for confirmation, directing the agent to modify the host system state (which may require privileged operations) even though it doesn't explicitly request sudo or account changes.