essay-polish
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [Prompt Injection] (SAFE): The skill contains no instructions to ignore safety filters or bypass system prompts. All instructions are contextually appropriate for essay editing.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or network-bound commands (like curl or wget) were found.
- [Indirect Prompt Injection] (INFO): The skill processes external essay content (Ingestion point: User-provided essay). Boundary markers are absent. Capability inventory: No tools, file-write, or network-access capabilities are defined. Sanitization is absent. Risk is negligible because the agent has no side-effect capabilities to exploit.
- [Unverifiable Dependencies & RCE] (SAFE): The skill consists of a single markdown file with no dependencies, remote script calls, or dynamic code execution patterns.
Audit Metadata