frame-problem
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses untrusted input to determine its internal logic flow.
- Ingestion points: Untrusted data enters the agent context through the $ARGUMENTS variable and via user responses gathered by the AskUserQuestion tool in SKILL.md.
- Boundary markers: The instructions do not define clear boundaries or provide explicit instructions for the agent to ignore potentially malicious commands embedded within the user's problem statement.
- Capability inventory: The skill's capabilities are limited to invoking other skills in a sequence (e.g., /investigate, /brainstorm, /troubleshoot). It does not have access to sensitive files, system administrative commands, or network operations.
- Sanitization: There is no logic present to sanitize or validate the user-provided input before it is used for domain classification.
Audit Metadata