discover

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill instructs scanning .env files and connection strings and then recording "signals" and repo details into outputs (ecosystem-map.md and .stackshift-batch-session.json) with no mention of redaction or reading secrets only via environment variables, so the agent would likely need to include discovered secret values verbatim in its generated outputs.

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly runs GitHub org repo and code searches via the GitHub API (see operations/github-ecosystem-search.md) and merges those user-generated, public GitHub results into the merge-and-score and presentation workflow (merge-and-score.md / present-ecosystem-map.md), so untrusted third-party content can directly influence scoring and next actions.