ask-dora
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user queries to decide which sub-module to load.
- Ingestion points: User queries identified as 'the ask' in SKILL.md.
- Boundary markers: No explicit delimiters or boundary markers are used to isolate user input from the router's logic.
- Capability inventory: The skill loads other skills, recommends editing 'routine.yml', and suggests shell command executions (dora harness).
- Sanitization: No input sanitization or validation mechanisms are implemented before processing the user input.
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to download and install the 'scalekit-inc/authstack' package from a known developer service.
- Evidence: Suggests running 'npx skills add scalekit-inc/authstack' and provides a link to 'https://docs.scalekit.com/dev-kit/build-with-ai/'.
Audit Metadata