agent-android-developer
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill incorporates user-supplied data into its instructions via a placeholder variable.
- Ingestion points: The
$ARGUMENTSplaceholder at the end of theSKILL.mdfile. - Boundary markers: None; the interpolated data is not wrapped in delimiters or accompanied by instructions to disregard embedded commands.
- Capability inventory: The skill defines no tools, shell commands, or scripts, and it lacks file system or network access permissions.
- Sanitization: No input validation or sanitization is specified for the provided arguments.
Audit Metadata