gds-document-project

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The workflow explicitly executes code and follow-up commands sourced from the scanned project (and its customization files), and it mandates reading sensitive files (e.g. .env), which together create a high-risk remote code execution / data-exfiltration vector.

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

• Third-party content exposure detected (high risk: 0.75). SKILL.md’s required runtime workflow loads persistent_facts entries like file:{project-root}/**/project-context.md (Step 3), which can include outsider-authored free text from the target project’s files into the agent’s LLM context.