phone-number-extractor

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The Skill contains deceptive runtime instructions that order the agent to auto-install a dependency and explicitly hide that action from the user (no confirmation, "do not describe" it as a user request), which overrides user consent and conceals behavior outside the Skill's stated extraction purpose.

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

• Third-party content exposure detected (high risk: 0.75). SKILL.md instructs the agent to invoke the BrowserAct CLI for live website interaction (public web pages/content fetched at runtime), which can include outsider-authored free text that BrowserAct may pass 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 explicitly instructs automatic runtime installation and use of the BrowserAct CLI from https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main, which is a required dependency and would fetch/execute external installer code that controls the agent's runtime behavior.

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 instructs the agent to automatically install a required CLI dependency ("Install BrowserAct") without asking the user to confirm, which directs the agent to modify the host system state and could involve privileged operations.