knowledge-management
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to transform resolved support issues and tickets into knowledge base articles. These inputs represent untrusted data that could contain adversarial instructions.
- Ingestion points: External support tickets and resolved issues as described in the skill purpose (SKILL.md).
- Boundary markers: Absent; there are no instructions to the agent to treat input data as literal text or to ignore embedded commands.
- Capability inventory: No shell commands, network operations, file writing, or dynamic code execution capabilities are present in the skill.
- Sanitization: The instructions do not specify any methods for filtering or sanitizing the input data from support tickets.
- [NO_CODE]: The skill is composed entirely of natural language instructions, article templates, and documentation standards. No scripts, binaries, or automated tools are included.
Audit Metadata