strobe-check
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Prompt Injection] (SAFE): The skill contains only task-specific instructions. No patterns of behavioral override, safety bypass, or system prompt extraction were found.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file path access, or network calls (curl, wget, etc.) are present in the skill.
- [Remote Code Execution] (SAFE): The skill does not perform any package installations or remote script executions.
- [Indirect Prompt Injection] (LOW): The skill is designed to ingest and analyze untrusted external data (manuscripts). While it lacks explicit boundary markers for this data, it also lacks any dangerous capabilities (e.g., file-write, network access, or command execution) that could be exploited via an injection attack.
- [Dynamic Execution] (SAFE): No runtime code generation, compilation, or unsafe deserialization techniques are used.
Audit Metadata