light-wait-what
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of instructional text and metadata configuration. There are no executable scripts, shell commands, or network operations present in the provided files. The instructions are focused on communication style and do not attempt to bypass safety filters or exfiltrate data.\n- [INDIRECT_PROMPT_INJECTION]: The skill references an external terminology source (
CONTEXT.md) which represents a data ingestion surface. This is evaluated as safe because the skill has no dangerous capabilities that could be leveraged by malicious content within that file.\n - Ingestion points:
CONTEXT.md(referenced inSKILL.md)\n - Boundary markers: None present\n
- Capability inventory: No tools, subprocesses, or network operations are enabled or used\n
- Sanitization: None present
Audit Metadata