copy-editing
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill is comprised of markdown instructional files, checklists, and JSON evaluation data. It contains no scripts, binaries, or automated shell commands.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided marketing copy, which constitutes an attack surface for indirect prompt injection if instructions are hidden within the analyzed text.
- Ingestion points: User-provided copy submitted for editing and review (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or "ignore instructions" wrappers for the processed content.
- Capability inventory: The skill does not possess sensitive capabilities such as network access, file system write permissions, or shell command execution, mitigating the risk of exploitation.
- Sanitization: No sanitization or filtering of input data is defined in the skill documentation.
Audit Metadata