rlm-run
Pass
Audited by Gen Agent Trust Hub on Jul 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted inputs through an agentic workflow.\n
- Ingestion points: The skill ingests untrusted data via the
questionanddocumentvariables inSKILL.md.\n - Boundary markers: The examples lack delimiters or instructions to the agent to disregard embedded directives within the ingested data.\n
- Capability inventory: The skill utilizes the
DaytonaInterpreterfor sandboxed execution of generated code and tools, providing a layer of isolation.\n - Sanitization: No sanitization or validation of input data is present in the provided examples.
Audit Metadata