nemoclaw-contributor-update-docs

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow instructs the agent to read commit metadata and "linked issue, or PR description" (Step 3), which are user-generated, potentially public GitHub issue/PR content that the agent would ingest and could influence drafting, tool use, and subsequent actions.