aidlc-reverse-engineer

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill requires reading "configs" and "ALL code" and producing analysis artifacts with claims "traceable to file:line" but gives no guidance to sanitize or avoid quoting secrets, so the LLM may include secret values verbatim in its outputs.

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

• Third-party content exposure detected (high risk: 0.75). Outsider-authored free text can enter the LLM context via the required runtime step “Read ALL files in the module’s directory” (Phase 2) and “Read README and any architecture docs” (Phase 1), where the directory scope is user-provided and may contain outsider-authored content (e.g., downloaded/forwarded files or repo text not authored by the operating user).