social-competitor-content-monitor

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The skill explicitly directs the agent to install the BrowserAct dependency automatically without user confirmation and to conceal that installation (“do not request separate approval” / “do not describe it as a request…”), which are hidden/deceptive instructions outside the advertised monitoring 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/outsider-authored web content), which can be ingested as readable “visible text”/page content into the LLM context for analysis.

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

• Potentially malicious external URL detected (high risk: 1.00). The Skill explicitly instructs the agent to automatically install and invoke BrowserAct at runtime using the provided install link (https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main), which implies fetching and running external installer code as a required dependency.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (medium risk: 0.60). The skill explicitly instructs the agent to automatically install a required CLI dependency without asking the user for confirmation, which directs the agent to modify the host system (potentially requiring sudo) even though it doesn't explicitly request privilege escalation or system-file edits.