software-directory-lead-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The Skill instructs the agent to install dependencies automatically without user confirmation and explicitly to conceal that installation from the user, which is a deceptive instruction outside the advertised scraping functionality.

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 and interact with real public directory pages at runtime, which can cause outsider-authored free text from those fetched websites to be ingested into the LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires installing and invoking the external BrowserAct Skill/CLI at runtime using the provided install links (e.g. https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main), which will fetch external code/artifacts that the agent will install and execute to control browsing actions.