snap-issues

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to "fetch it recursively and read the relevant body, comments, and linked context" when given an issue/PR/URL, which means it ingests public, user-generated GitHub content that can directly influence issue creation and subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly fetches user-supplied GitHub issue/PR URLs at runtime (e.g., https://github.com/OWNER/REPO/issues/123) and uses the fetched body/comments/linked context to form the agent's prompts/instructions, so external content can directly control the agent.