skill-writer

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

• Third-party content exposure detected (high risk: 0.85). The required workflow includes fetching and reading a public web page at runtime (https://agentskills.io/specification), which is outsider-authored free text that the agent ingests into its LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires checking and treating the fetched content from https://agentskills.io/specification as authoritative "during every run," so runtime-fetched external content directly controls the agent's instructions and behavior.