writing-communication-council
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
- Indirect Prompt Injection (LOW): The skill processes untrusted user-supplied text for editing and review. It lacks specific boundary markers to prevent the agent from acting on commands embedded in that text. However, because the skill has no executable or network-based capabilities, the impact is limited to text generation.
- Ingestion points: User text provided for review in SKILL.md.
- Boundary markers: Absent.
- Capability inventory: No subprocesses, network calls, or file-system write capabilities.
- Sanitization: Absent.
Audit Metadata