interrogate

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt requires packaging and embedding diffs or file contents into reviewer prompts (including sending them to multiple subagents), which will force the LLM to include any embedded secrets (API keys, tokens, passwords) verbatim in its generated messages.

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md’s required workflow ingests free text only from the user’s provided scope/context plus the code diff/file contents it is asked to review, which are directly user-authored inputs into the prompt template.