token-budget-advisor
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates entirely through natural language instructions to manage response length and depth. It does not include any executable scripts, system commands, or network operations.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user prompts to determine the desired response depth. While it lacks explicit boundary markers for user data, it also lacks any exploitable capabilities like command execution, file system access, or network operations that could be abused via injection.
- [SAFE]: The external link provided is a reference to the documentation and source repository and is not used for downloading or executing remote content during the skill's operation.
Audit Metadata