internal-comms
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Prompt Injection] (SAFE): The instructions are strictly focused on formatting internal communications like newsletters and FAQs. There are no attempts to override system prompts or bypass safety filters.
- [Data Exposure & Exfiltration] (SAFE): No sensitive file paths, hardcoded credentials, or network-bound operations were detected. The skill references local documentation files in an
examples/directory. - [Remote Code Execution] (SAFE): The skill does not contain any scripts, package manifests, or commands to download/execute remote content.
- [Indirect Prompt Injection] (SAFE):
- Ingestion points: User-provided text intended for internal communication drafts.
- Boundary markers: None explicitly defined in the top-level SKILL.md.
- Capability inventory: None. The skill does not possess the ability to write files, execute commands, or access the network.
- Sanitization: Not applicable as the skill has no functional side-effects beyond text generation.
- [Obfuscation] (SAFE): No encoded strings, hidden characters, or homoglyphs were found in the text or metadata.
Audit Metadata