dt-app-dashboards
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes dashboard JSON documents retrieved from an external server, which introduces a risk of indirect prompt injection if the content contains malicious DQL queries or instructions.
- Ingestion points: Dashboard content is fetched via
dtctl get dashboardas instructed inSKILL.mdandreferences/create-update.md. - Boundary markers: The skill provides an example JSON structure in
SKILL.mdand instructions to inspect available properties. - Capability inventory: The skill utilizes
dtctl queryto execute DQL,dtctl applyto update server-side resources, and performs local file system operations (write/read/delete) fordashboard.json. - Sanitization:
references/create-update.mdspecifies a mandatory DQL validation process usingdtctl querywith the--plainflag and advises using single quotes for shell command safety.
Audit Metadata