aco-design-guidelines

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs the agent to WebFetch and apply live guidelines from the public URL https://raw.githubusercontent.com/gustav-glitch/aco-design/main/markdown.md before each review, so untrusted third‑party content is read and used to determine checks and output formatting and thus could inject instructions that influence agent behavior.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly fetches runtime guidelines from https://raw.githubusercontent.com/gustav-glitch/aco-design/main/markdown.md and uses that fetched content as the authoritative rules and output-format instructions the agent must follow, so the external file directly controls agent prompts and is a required runtime dependency.