The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes a local utility script, scripts/sequence_analyzer.py, to perform static analysis on email sequences. The script processes JSON data to calculate quality scores based on subject line length, call-to-action (CTA) presence, and spam keyword detection. It relies entirely on standard Python libraries (argparse, json, re, sys) and does not perform network operations or access sensitive system files.
[INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface as it processes external marketing context (e.g., .claude/product-marketing-context.md) and user-provided campaign goals. While this data could theoretically contain instructions to influence the agent's output, the skill lacks high-privilege capabilities (like network access or arbitrary code execution) that would make such an injection high-risk. The processing is governed by clear task-specific instructions and static scoring rules.
[SAFE]: No obfuscation, persistence mechanisms, or credential harvesting patterns were found. The tool integrations mentioned (e.g., Mailchimp, Resend) are standard industry services, and the script handles data locally without external dependencies.

email-sequence