agnt-cli-builder

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to extract connect codes or tokens from the prompt and immediately run commands like "agnt connect " or "agnt login --token ", which requires the LLM to emit secret values verbatim in its output/commands and thus creates an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.85). At runtime the skill’s required workflow ingests outsider-authored free text from public GitHub PR content via gh search prs ... and gh pr view ... (PR titles/bodies/comments/reviews/status fields are read and then used in the agent’s LLM context).