cold-email-weekly-rhythm

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute several local shell commands using npx tsx to manage email inbox health and perform deliverability tests (e.g., scripts/list-health.ts, scripts/tag-inboxes.ts, scripts/run-spam-test.ts).
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) as it involves processing untrusted data from external email replies through the /positive-reply-scoring tool.
  • Ingestion points: Email replies categorized as positive_interested, positive_soft, positive_referral, or negative_hostile are processed to determine follow-up actions.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are defined in this orchestration playbook.
  • Capability inventory: The skill environment has the capability to execute shell commands (npx tsx) and perform file system operations (writing to .json, .csv, and .md log files).
  • Sanitization: There is no evidence of sanitization or validation of the email content before it is processed by the scoring tool or recorded in the experiment logs.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 10:21 AM
Security Audit — agent-trust-hub — cold-email-weekly-rhythm