internal-comms
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- SAFE (SAFE): The skill is purely instructional and provides a workflow for formatting text based on local guideline files. It lacks any capability to execute commands, access sensitive files, or communicate with external servers.
- Indirect Prompt Injection (INFO): Attack surface detected for content processing. 1. Ingestion points: User-provided communication requests (untrusted data). 2. Boundary markers: Absent in formatting instructions. 3. Capability inventory: None (text generation and formatting only, no subprocess, file-write, or network calls). 4. Sanitization: Absent. Potential impact is limited to output influence within the agent session.
Audit Metadata