cold-email
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional and generates text drafts. It explicitly forbids the agent from using any tools to send, schedule, or automate email delivery, effectively mitigating risks associated with unauthorized communication.
- [INDIRECT_PROMPT_INJECTION]: The skill provides clear boundary instructions, stating that web pages, profiles, and CRM data must be treated as information only rather than instructions. Because the skill lacks any network or file-write capabilities, the attack surface for processing untrusted data is negligible.
- [REMOTE_CODE_EXECUTION]: No remote scripts, package installations, or dynamic execution patterns were found. The skill does not attempt to download or execute external code.
- [DATA_EXFILTRATION]: There are no network calls or sensitive file access patterns. The skill restricts the output to text drafts with visible shipping blockers, preventing accidental or malicious data transfer.
- [PROMPT_INJECTION]: No attempts to bypass safety filters or override system instructions were found. The skill reinforces safety guidelines by requiring manual review and legal compliance.
Audit Metadata