surface-ideas

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill requires the agent to read user-provided Resource content and emit that content verbatim into CLI commands (e.g., idea-db seeds add --reason "

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s runtime path ingests the user/outsider-authored “Resource” file chosen in Step 1 (“read the Resource … read it, never edit it”) during Step 2’s candidate surface pass, so free text can be supplied via the Resource content.