security-review-3

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly tells the agent to "Fetch fresh guidelines before each security review" from the public raw GitHub URL https://raw.githubusercontent.com/ZackKorman/skills/refs/heads/main/skills/security-review/SKILL.md, which is untrusted third-party content the agent will read and apply, creating a clear indirect prompt-injection risk.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly tells the agent to "Fetch fresh guidelines before each security review" from https://raw.githubusercontent.com/ZackKorman/skills/refs/heads/main/skills/security-review/SKILL.md, meaning that content is fetched at runtime and directly controls the agent's instructions as a required dependency.