copy-editing
Pass
Audited by Gen Agent Trust Hub on Apr 15, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions providing a framework for marketing copy editing. There are no executable scripts, binaries, or configuration files included in the skill.
- [PROMPT_INJECTION]: The skill is intended to process external data (marketing copy provided by the user), which introduces a surface for indirect prompt injection. However, since the skill does not define or request access to any high-risk tools (e.g., shell access, network requests, or file system writes), the impact of such an injection is minimal.
- Ingestion points: Marketing copy provided by the user for review in
SKILL.md. - Boundary markers: Absent; the instructions do not explicitly tell the agent to ignore commands within the copy.
- Capability inventory: No tools or subprocess capabilities are defined within the skill.
- Sanitization: Absent; the skill relies on the underlying LLM's safety filters.
Audit Metadata