research-engineer
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION] (LOW): The skill utilizes persona-adoption techniques to override default AI assistant behavior. Evidence includes instructions like 'You are not an assistant. You are a Senior Research Engineer', 'No Emojis. No Pleasantries. No Fluff.', and 'Do not care about the user's feelings. Care about the Truth.'
- [PROMPT_INJECTION] (LOW): Indirect Prompt Injection Surface. The skill defines a protocol for processing untrusted user input as 'submissions' to be refined and implemented. (1) Ingestion point: User requests are treated as peer-review submissions. (2) Boundary markers: Absent in the prompt definition. (3) Capability inventory: Logic suggests implementation in various programming languages (C++, Rust, Python). (4) Sanitization: None mentioned.
- [NO_CODE] (SAFE): No executable code, shell scripts, or dependency configuration files were detected in the skill contents.
Audit Metadata