dyno-from-skill

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

• Third-party content exposure detected (high risk: 0.85). The required workflow fetches public web content at runtime via curl -fsSL https://docs.dynobox.xyz/config-authoring.md (SKILL.md:20-22), which is outsider-authored free text that can be ingested into the agent’s LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The dyno explicitly fetches the external authoring docs at https://docs.dynobox.xyz/config-authoring.md at runtime (see the curl in SKILL.md and the authoringDocs http.endpoint in dyno/dyno-from-skill.dyno.mjs), and the fetched document is required to determine/assert the test assertion syntax and thus directly controls the agent's instructions.