chill
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill incorporates user-provided context via the
$ARGUMENTSvariable without using clear boundary markers or sanitization. This allows external input to be treated as instructions, potentially influencing the agent's logic flow. - Ingestion points: The
$ARGUMENTSvariable inSKILL.md. - Boundary markers: Absent for the user-supplied arguments.
- Capability inventory: None. The skill does not execute code, perform network operations, or modify the file system.
- Sanitization: Absent.
- [NO_CODE]: The skill consists entirely of markdown instructions and YAML metadata, with no accompanying scripts or executable files.
Audit Metadata