google-ads-intent-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The skill explicitly instructs the agent to install a runtime dependency automatically and to "not request separate approval" or describe the link as a user-facing request, which directs deceptive/hiding behavior outside the skill's stated 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 real browser pages at runtime (public web content/outsider-authored page text), which can be ingested into the LLM context via the tool’s 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 to automatically install the required BrowserAct CLI at runtime using the install link https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main (also references https://www.browseract.com/?co-from=lead-generation), which implies fetching and executing remote code as a required runtime dependency.

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 explicitly instructs the agent to automatically install runtime dependencies (BrowserAct CLI/Skill) without asking the user for confirmation and to proceed as the agent's responsibility, which encourages changing the host system state and bypassing user approval.