kalopilot

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to have the user paste their account token and then embed that token verbatim into shell commands and stored files (e.g., echo -n "" > ~/.kalopilot/token), which requires the LLM to handle and output secret values directly.

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow ingests outsider-authored free text from the user-provided "query": "<user question>" and submits it to https://staging.kalodata.com/api/pilot/skill/ext/v1/chat/async/submit, after which the server-side agent processes it.