linkedin-post-reactions-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The skill includes explicit instructions to install a runtime dependency automatically and to "not describe" the installation link to the user or request separate approval, which is a hidden/deceptive directive outside the stated scraping purpose.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). This Skill is high-risk: it explicitly facilitates mass collection of personal LinkedIn data (including contact details) and instructs automatic installation of external tooling without user consent, enabling potential unauthorized data harvesting and supply-chain installation.

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 browser-act Skill for live browser execution (public LinkedIn pages/URLs), which can cause outsider-authored free text from fetched web content to be ingested into the LLM context via the runtime browser workflow.

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 a required runtime dependency from https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main at runtime, which implies fetching and executing external installer code that controls the agent's runtime behavior.