communicate
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of markdown instructions and reference files that provide stylistic and structural writing advice. It does not invoke shell commands, perform network requests at runtime, or modify system configurations.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided drafts and requests for writing assistance. This creates an ingestion surface for untrusted data. However, the risk is negligible because the skill does not utilize any exploitable capabilities like script execution, file writing, or external data transmission.
- Ingestion points: User-provided writing drafts and requests as defined in
SKILL.md. - Boundary markers: No explicit delimiter or instruction-guarding markers are required for user data.
- Capability inventory: The skill uses no external tools, shell commands, or network operations.
- Sanitization: No input sanitization or filtering is performed on user content.
Audit Metadata