awesome-openclaw-agents-templates

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly shows agents that fetch and act on user-generated third-party content—for example the "prReviewerAgent" workflow (github.pull_request.opened → "Fetch PR diff", analyze code changes, post review) and examples that collect Slack responses or search external knowledge bases—so the agent is expected to ingest untrusted third-party content that can change its actions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill's setup explicitly clones and installs code from https://github.com/mergisi/awesome-openclaw-agents and then reads SOUL.md from that repository into soulConfig which is injected as the model's system prompt at runtime, so externally fetched content directly controls agent prompts and is a required dependency.