ghostwriter
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions defining a ghostwriting workflow. It does not utilize any scripts, commands, or network-enabled tools.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-supplied writing samples, which introduces a surface for indirect instructions. However, because the skill lacks executable capabilities, this surface is not exploitable.
- Ingestion points: User-provided writing samples collected in Step 1 of
SKILL.md. - Boundary markers: None specified for the analysis of samples.
- Capability inventory: No capabilities identified; the skill does not use filesystem access, network operations, or subprocess execution.
- Sanitization: No specific sanitization methods are mentioned for the incoming text samples.
Audit Metadata