kuaishou-comment-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The Skill contains explicit instructions to auto-install a dependency without asking the user and to avoid describing or requesting approval for that installation, which are hidden/deceptive directives outside its 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 live Kuaishou pages and extract visible comment text (outsider-authored free text from public web pages) into the agent’s runtime context for processing/export.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent at runtime to automatically use the install link https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main to obtain the required BrowserAct Skill/CLI, which would fetch and install remote code that the skill depends on.

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

• Attempt to modify system services in skill instructions detected (high risk: 0.80). Flagged because the Skill instructs the agent to automatically install the BrowserAct dependency and resume execution without asking the user for confirmation, which requires modifying the host system (potentially needing elevated privileges) and thus encourages autonomous state changes.