repo-scanner

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly runs a grep that matches API key patterns (e.g., "sk-") across repo files (including .env files) and its reporting rules require file:line references, which forces the agent to read and potentially output secret values verbatim.

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow “Repo Scanner” reads a user-supplied repository’s files directly at runtime (e.g., find . -type f ... plus checks of README.md, package.json, config files), so outsider-authored free text in that repo can be ingested as part of the scan.