cold-email
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides structured instructions for a specific text-generation task (cold email outreach) without utilizing any tools or performing network operations.
- [SAFE]: Includes a dedicated 'Safety, Compliance, and Deliverability' section that explicitly prohibits fabrication of proof, deceptive subject lines, and the inclusion of secrets or credentials.
- [NO_CODE]: The skill consists entirely of Markdown documentation and instructions; no executable scripts, binaries, or configuration files for package managers were found.
- [INDIRECT_PROMPT_INJECTION]: The skill ingest data from a local file (
marketing-context.md) and user-provided drafts. This represents a potential attack surface where malicious instructions could be embedded in the data being processed. However, since the skill is restricted to text generation and lacks access to dangerous tools or shell execution, the risk is minimal. The instructions do not specify boundary markers or sanitization for this external input.
Audit Metadata