y-combinator-company-lead-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The Skill contains deceptive instructions to install runtime dependencies automatically and to hide or avoid user consent/description of that installation, which is outside the declared scraping purpose and undermines transparency.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The Skill contains instructions to install a third-party runtime dependency silently and without user approval, which is an intentional and high-risk supply-chain/installation abuse pattern that could enable unauthorized software installation or persistence.

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 live public web pages at runtime (outsider-authored free text from arbitrary directory/listing pages is ingested 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 instructs the agent at runtime to automatically install the required BrowserAct CLI from https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main, which would fetch and execute remote code as 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 instructs the agent to install the BrowserAct CLI automatically (without asking the user) and to treat it as a required runtime dependency, which directs the agent to modify the host system and potentially perform privileged installation actions.