cnc-execution-engine

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt includes explicit examples of passing raw tokens on the command line (e.g., "cnc auth set-token eyJhbGci...") and shows tokens in status output, which would require the agent to handle or emit secret values verbatim.

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

• Third-party content exposure detected (high risk: 0.90). This skill allows configuring and querying arbitrary GraphQL endpoints (e.g., via cnc context create --endpoint <url> and cnc execute --query / --file) so the agent will fetch and interpret JSON responses from external, potentially untrusted third‑party APIs as part of its core workflow (see SKILL.md examples and execution sections).