using-hyper
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill employs high-pressure and non-negotiable instructional reinforcement, using phrases like 'ABSOLUTELY MUST', 'not negotiable', 'not optional', and 'automatic failure' to override the agent's standard operating procedures and decision-making framework.
- [PROMPT_INJECTION]: It mandates a rigid 'First Response Protocol' that dictates a specific mental checklist the agent must perform before every interaction, which is a technique designed to prioritize the skill's logic over system-level instructions.
- [PROMPT_INJECTION]: The skill commands the agent to follow loaded skills 'exactly as written' and explicitly forbids 'rationalizing' or deviating from them, creating a vulnerability where any instructions (including potentially malicious ones) within a loaded skill file would be executed without critical evaluation.
- [PROMPT_INJECTION]: Ingestion points: The agent is instructed to load content from other skill files using the Skill tool based on task context. Boundary markers: There are no delimiters or 'ignore embedded instructions' warnings specified for the content being loaded. Capability inventory: The skill directs the agent to perform comprehensive tasks including code implementation, bug fixing, and verification through the loaded workflows. Sanitization: No sanitization or validation logic is present to filter content from the loaded skill files before execution.
Audit Metadata