workflow-config
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input via the
$ARGUMENTSparameter to configure and persist workflow settings to the agent's memory system.\n - Ingestion points: The
$ARGUMENTSvariable inSKILL.mdis used to capture configuration choices from the user.\n - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the input strictly as data or to ignore instructions embedded within the user's preference string.\n
- Capability inventory: The skill uses the agent's native memory persistence mechanism and has access to standard file system tools (
Read,Grep,Glob).\n - Sanitization: No explicit sanitization or validation steps are defined for the input before it is written to the agent's persistent memory.
Audit Metadata