token-budget-allocator
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a defensive utility and instructional guide for token management. It does not perform network operations, access sensitive files, or execute untrusted code.
- [INDIRECT_PROMPT_INJECTION]: The provided Python implementation contains a surface for interpolating external data (RAG context and message history) into a prompt payload. However, this is documented as a token-counting utility and includes boundary markers (e.g.,
[CONTEXT]:). The skill does not include any capabilities (such as subprocess calls, file writes, or network requests) that could be exploited via indirect prompt injection.
Audit Metadata