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
Risk Level
SAFE
Analyzed
Mar 9, 2026, 01:22 AM