agent-desktop-developer
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill is entirely comprised of markdown-based instructions and metadata. It does not include any scripts, executables, or configurations that perform automated actions on the host system.
- [INDIRECT_PROMPT_INJECTION]: The skill uses the
$ARGUMENTSplaceholder to interpolate user tasks. This is a standard pattern for defining the agent's work surface. Because the skill does not grant the agent additional tools, write permissions, or network access beyond its default environment, the risk associated with processing untrusted input in this specific context is negligible.
Audit Metadata