reply-handling
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides a legitimate framework for automating and managing cold email responses using established sales methodologies like Command of the Message and SPICED. The included script
scripts/check-output.pyis a standard utility function that performs local file reads on user-provided paths to verify deliverable keywords; it does not access sensitive system files or exfiltrate data. - [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to process and categorize external email replies. While this introduces a potential attack surface for indirect prompt injection, the instructions include a specific "Category 8" for spam, abuse, and manual review, effectively mitigating the risk of automated obedience to malicious content in replies.
Audit Metadata