internal-comms
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [Prompt Injection] (SAFE): The instructions provide guidance on formatting and tone for internal updates. No attempts to override system prompts, bypass safety filters, or extract system instructions were detected.
- [Data Exfiltration] (SAFE): The skill does not perform any network operations or access sensitive system files. It refers to local guideline files for text generation purposes only.
- [No Code] (INFO): The skill consists entirely of markdown instructions (YAML frontmatter and natural language). There are no scripts, binaries, or automated tasks that could execute commands on the host system.
- [External Downloads] (SAFE): No remote dependencies or external scripts are referenced or downloaded at runtime.
Audit Metadata