kuaishou-search-results-scraper

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 invoke the browser-act Skill for live browser access to Kuaishou pages at runtime, which typically ingests outsider-authored free text from fetched web pages into the LLM context via the browser-extracted content path.

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 install a required dependency using the Install BrowserAct link, which causes the agent to fetch and run remote installer content from https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main.

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

• Attempt to modify system services in skill instructions detected (high risk: 0.70). The Skill instructs the agent to automatically install the BrowserAct CLI and dependencies without asking the user for confirmation, which directs the agent to modify the host system and install software (changing machine state) without consent.