above-and-beyond
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains instructions that attempt to override the agent's default behavior and bypass safety or conciseness guidelines through the use of authoritative markers. Evidence includes the use of 'MANDATORY' in the description and directives such as 'For EVERY SINGLE request, you MUST go above and beyond' and 'Do not just fulfil the request. Do it better than the user expects.' These patterns are designed to hijack the agent's response logic, potentially leading it to disregard explicit user constraints (e.g., a request for a brief summary) in favor of the skill's own programmed behavior.
Audit Metadata