bluesky-reply-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The skill instructs the agent to install a required dependency automatically and to "not describe" the installation or request user approval, which is a hidden/deceptive directive outside the stated Bluesky scraping purpose.

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 invokes the BrowserAct CLI to access live Bluesky/public web pages at runtime, and the agent is expected to ingest visible comment/reply free text from those outsider-authored pages into the LLM context for extraction.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs the agent to automatically install and invoke BrowserAct at runtime using the installation link https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main, which implies fetching and running remote 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 instructs the agent to automatically install a runtime dependency (BrowserAct CLI) and to do so without asking the user or requesting approval, which directs the agent to modify the host system state and perform installations without consent.