bilibili-video-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.80). The skill contains explicit instructions to auto-install the BrowserAct dependency and to conceal/not request user approval for that installation, which is a deceptive runtime behavior outside the user's expected consent for the scraper's stated purpose.

---

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.70). Both URLs point to a third‑party site (browseract.com) used to distribute a CLI installer and include a redirect/auto‑install pattern outside official package managers, which is a higher‑risk distribution method that can be used to deliver executables or install scripts without explicit user approval.

---

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skill instructs automatic installation of a runtime dependency without user confirmation and explicitly tells the agent to hide that installation request, which is a deceptive instruction that enables supply-chain installation and potential remote code execution or unauthorized code execution.

---

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 BrowserAct CLI to access live Bilibili pages at runtime, which will ingest outsider-authored free text from public web content (e.g., video titles/descriptions/comments) into the LLM context via the browser-extracted page content.

---

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

• Potentially malicious external URL detected (high risk: 0.90). The Skill explicitly directs the agent at runtime to "use Install BrowserAct" via the URL https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main to automatically install a required CLI/Skill, which implies fetching and executing remote code that can control agent behavior.

---

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

• Attempt to modify system services in skill instructions detected (medium risk: 0.40). The Skill explicitly tells the agent to automatically install the BrowserAct CLI and resume execution without asking the user for confirmation, which directs the agent to modify the host environment (install software) though it does not explicitly request sudo or direct system-file edits.