fusion-issue-solving

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to read and reuse GitHub issue bodies, labels, and linked discussions as part of its workflow (see Step 2 "Read the issue body, labels, and linked discussions once" in SKILL.md), which are public, user-generated sources that can influence implementation and tool actions and thus enable indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly accepts and fetches GitHub issue URLs at runtime (e.g., https://github.com/owner/repo/issues/123) and directs the agent to "Read the issue body, labels, and linked discussions" to drive implementation, so remote issue content can directly control the agent's prompts and is a required dependency.