build-app-context

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to read secrets from files/env and place them verbatim into Authorization headers (Basic base64(TESTRAIL_USER:TESTRAIL_API_KEY), Bearer {GITHUB_TOKEN}, etc.) for API requests, requiring the LLM to handle and emit secret values directly.

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

• Third-party content exposure detected (high risk: 0.85). The skill fetches outsider-authored free text from public/third-party sources at runtime—specifically GitHub repository files (README/docs/feature files/translations) and Jira issue descriptions/acceptance criteria via their REST APIs—which is then parsed and written into the LLM context for distillation.