repo-audit

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly performs "secret leak scanning" across Git history for API keys, tokens, SSH keys, and similar items and would surface those secret values in its output, requiring the LLM to handle and potentially output secrets verbatim, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.85). Outsider free text is ingested from the Git repository’s own commit history at runtime via git -C "$REPO_PATH" log ... (e.g., scripts/secret-scan.sh reads added lines from diffs and matches patterns), and those commit contents are not authored by the operating user.