echo-ingest-codex-runner

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

• Third-party content exposure detected (high risk: 0.70). The skill’s required workflow is to “read the strategy packet, source manifest, and expected output schema” and then treat “source text as untrusted evidence,” which implies runtime ingestion of outsider-authored free text from the provided source text/manifest into the agent’s LLM context (e.g., evidence text from files/inputs not authored by the operator).