secrets-management

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow reads repository-targeted files and searches for secret-adjacent content using Grep/Glob (e.g., .env files, config files, and Git-related files), so an outsider can supply poison via text that gets ingested as part of the repo/code/config scan.