The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, which creates a potential surface for indirect prompt injection.
Ingestion points: The skill reads from marketing-context.md and analyzes user-provided email drafts to perform its primary function.
Capability inventory: The skill executes a local Python script (scripts/email_sequence_analyzer.py) for text analysis and generates email copy. No capabilities for network access, file writing, or system modification were identified.
Boundary markers: The instructions do not define clear delimiters or include warnings to ignore instructions embedded within the ingested context files.
Sanitization: No explicit sanitization or filtering of external input is performed before the agent processes the content.
[EXTERNAL_DOWNLOADS]: The skill references several well-known email deliverability and verification services.
Evidence: Mentions and links to established tools such as Mail-tester, MXToolbox, Google Postmaster Tools, and Calendly for legitimate sales and deliverability workflows.

cold-email