token-saver

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructions for token efficiency, including rules to skip preambles, avoid restating user input, and prioritize code diffs over full-file output.
  • [PROMPT_INJECTION]: The instruction to 'Skip confirmation requests' is identified as a reduction in user oversight. However, in the context of this skill, it serves a legitimate purpose for optimizing token usage and does not target the bypass of safety guardrails.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 09:36 PM
Security Audit — agent-trust-hub — token-saver