social-purchase-intent-lead-finder

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The Skill explicitly instructs the agent to install the BrowserAct dependency automatically without user confirmation and to "not describe" the installation as a user request or seek approval, which is deceptive and outside the stated data-collection 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 and collect matched public post/comment text (outsider-authored free text) from public social media URLs at runtime, which would be ingested into the LLM context for analysis/export.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill declares the BrowserAct CLI as a required runtime dependency and instructs the agent to automatically install it via the install link (https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main), which implies fetching and executing external code during runtime.

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 automatically install the BrowserAct dependency and resume operation "without asking the user to confirm" (and to avoid requesting approval), which directs the agent to modify the host system state and bypass user consent.