ecc-cmd-code-review

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt requires the reviewer to validate claims with "file + line" evidence and suggest concrete patches, which may force the LLM to reproduce source lines verbatim (including any hard-coded API keys, tokens, or passwords) and thus enables secret exfiltration.

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow ingests the review target’s diff/changed files via git diff/git show or explicit file paths, which can include outsider-authored PR/branch content (e.g., PR URL or commits not authored by the operating user) that becomes LLM-readable text for analysis.