system-health
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources such as GitHub and Figma which could contain malicious instructions.
- Ingestion points: External data from GitHub (issues, PRs), Figma (analytics, variables), and npm (trends) are pulled into the agent's context as described in the Auto-pull integrations section.
- Boundary markers: The instructions lack delimiters or specific warnings to ignore instructions embedded in the pulled data.
- Capability inventory: The skill has the ability to read project configuration files (.ds-ops-config.yml) and write health reports to the file system.
- Sanitization: No sanitization logic is defined for the external data before it is incorporated into the health assessment report.
Audit Metadata