agile-router
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill ingests untrusted user input via the
$ARGUMENTSvariable to determine which agile skill to recommend, creating a surface for indirect prompt injection. - Ingestion points: The
$ARGUMENTSplaceholder is used inSKILL.mdto receive context from the user. - Boundary markers: Absent; there are no delimiters or specific instructions to help the model distinguish between user data and routing instructions.
- Capability inventory: The skill is restricted to making text-based recommendations for internal slash commands and does not have access to subprocesses, file-writing, or network operations.
- Sanitization: No sanitization or validation of the input is performed before processing.
Audit Metadata