goal-setter
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, code obfuscation, or unauthorized data access behaviors were identified. The skill consists entirely of instructional prompts aimed at task structuring.
- [DATA_EXPOSURE]: The skill includes explicit security guidelines to prevent the exposure of sensitive information. It instructs the agent to avoid using real keys, tokens, or private data unless authorized and specifically warns against including such data in verification evidence.
- [PROMPT_INJECTION]: No evidence of prompt injection or instructions to bypass safety filters was found. Instead, the skill encourages setting strict boundaries and permissions for downstream tasks.
- [COMMAND_EXECUTION]: The skill does not contain executable scripts or commands. It functions as a meta-prompting tool to guide the generation of task descriptions for other agents.
Audit Metadata