youtube-community-post-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The Skill instructs the agent to install the BrowserAct dependency automatically and explicitly to "not ask the user to confirm" and to "not describe" the installation as a request to open their browser, which are deceptive, hidden directives unrelated to the described 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 the BrowserAct CLI to access live YouTube pages at runtime and extract visible post text/captions/descriptions (outsider-authored public web content), which would be ingested into the LLM context for processing.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires installing the BrowserAct CLI at runtime and directs the agent to "install the missing dependency automatically" via https://www.browseract.com/?co-from=social-media (and a redirect variant https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main), which is a remote installer URL that would be fetched during runtime to obtain and execute code for a required dependency.

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

• Attempt to modify system services in skill instructions detected (high risk: 0.80). The skill explicitly directs the agent to automatically install the BrowserAct CLI and resume execution "without asking the user to confirm," which pushes the agent to perform system-level changes (software installation) on the host and could trigger privileged operations or modify system state.