cold-email
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is composed entirely of markdown instructions and reference data for copywriters. There are no executable files, scripts, or configurations that would trigger tool usage or system commands.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied data to generate email copy. While this constitutes a vulnerability surface for indirect prompt injection, the skill lacks the capabilities required to perform harmful actions (e.g., no network access, no file system writes, and no shell execution).
- Ingestion points: User-provided prospect information and local files such as .agents/product-marketing.md.
- Boundary markers: None defined.
- Capability inventory: No tool usage, network access, or shell commands are defined in the skill files.
- Sanitization: None implemented.
Audit Metadata