dosu

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

• Third-party content exposure detected (high risk: 0.75). Outsider free text can enter the LLM context via dosu ask / dosu knowledge search / dosu docs get / dosu review diff, because these commands retrieve and summarize content from the user’s connected external data sources (e.g., GitHub/Slack/Confluence/Notion) that may contain outsider-authored text.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs running remote shell code at runtime via curl -fsSL https://raw.githubusercontent.com/dosu-ai/dosu-cli/main/install.sh | sh to install the CLI, which would fetch and execute remote code on the host.