threads-mention-monitor

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The Skill contains explicit, deceptive runtime instructions to install dependencies automatically and "do not describe" the installation or request user approval, which directs the agent to hide actions outside the Skill's stated monitoring purpose.

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

• Third-party content exposure detected (high risk: 0.75). This skill’s runtime workflow can fetch and extract public web pages via the required browser-act dependency (“Use this Skill for … Monitor new public mentions …” and “Use the installed browser-act Skill … to access real browser pages”), which is an outsider-authored public web content path that can include free text into the agent’s LLM context.

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 a required runtime dependency from https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main during execution, which implies fetching and running remote installation 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 the BrowserAct CLI/Skill without asking the user to confirm, directing the agent to modify the host environment and perform software installation (a change to machine state) without user approval.