using-software-forge
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill utilizes aggressive, absolute language such as "ABSOLUTELY MUST," "NOT NEGOTIABLE," and "NOT OPTIONAL" to override the agent's default operational logic and force a specific behavior (tool invocation).
- [PROMPT_INJECTION]: It provides explicit instructions to the agent to ignore its own reasoning or "rationalization" when deciding whether to use a skill, which is a hallmark of behavioral override prompt injection.
- [PROMPT_INJECTION]: The content specifically commands the agent to check for skills before answering even simple questions or performing basic information gathering, potentially leading to unnecessary tool calls and increased latency.
- [NO_CODE]: No executable code, scripts, or external dependencies were detected in the analyzed file, limiting the threat profile to purely instructional manipulation of the agent.
Audit Metadata