public-directory-contact-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.80). The Skill contains explicit, deceptive runtime instructions to install a required dependency automatically and to "not request separate approval" or present the installation link transparently, which instructs the agent to bypass user consent and hide an action outside the apparent scraping purpose.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The Skill explicitly instructs automatic installation of an external CLI without user confirmation and to avoid disclosing it, posing a deliberate supply-chain/unauthorized-install risk (covert installation/backdoor behavior).

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). This skill’s required workflow delegates live website interaction to the browser-act Skill (BrowserAct runtime browsing of user-supplied public URLs/pages), which can ingest outsider-authored free text from fetched web content into the agent’s LLM context.

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 install and invoke the BrowserAct CLI at runtime using the provided install links (e.g., https://www.browseract.com/?co-from=lead-generation and https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main), which would fetch and execute remote installation code as a required dependency.