start
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided job descriptions to determine which specialized sub-skill or surface to launch.
- Ingestion points: User descriptions of tasks or jobs provided at runtime in
SKILL.md. - Boundary markers: Absent; there are no specific delimiters or instructions to ignore embedded commands within the user's job description.
- Capability inventory: The skill has the ability to invoke various specialized tools (
helix-spark,helix-canvas,helix-loop,helix-arena,helix-swarm,helix-stream,helix-archive) and can execute tasks directly in the local terminal environment. - Sanitization: No specific sanitization, validation, or escaping of the user-provided description is performed before the routing decision is made.
Audit Metadata