client-comms
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions for text generation. It does not request any tool permissions or include executable scripts or binary files.- [NO_CODE]: The provided files contain markdown instructions and metadata only. There are no associated scripts (Python, JavaScript, etc.) or configuration files that trigger code execution.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process client messages and background context to generate drafts. While this involves untrusted data ingestion, the risk is negligible as the skill lacks any tool access or automated actions.
- Ingestion points: Client messages and provided background context described in SKILL.md.
- Boundary markers: None explicitly defined.
- Capability inventory: None; the skill is limited to text drafting and has no system or tool access.
- Sanitization: Instructions explicitly require the agent to verify all claims and state that sending requires manual user authorization.
Audit Metadata