The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were detected in the skill instructions or execution flow.
[PROMPT_INJECTION]: The skill does not contain instructions to override safety filters, disregard previous instructions, or extract system prompts. The execution flow is strictly focused on prospect research and message drafting.
[DATA_EXFILTRATION]: No unauthorized network operations or access to sensitive local files (such as SSH keys or AWS credentials) were identified. The use of CRM and Enrichment connectors is for the skill's stated primary purpose.
[COMMAND_EXECUTION]: The skill does not execute arbitrary shell commands or use dynamic execution patterns like eval() or exec(). It interacts with other skills and platform tools through defined interfaces.
[REMOTE_CODE_EXECUTION]: No external script downloads or package installations from unknown sources are present. The internal dependency on the research-prospect skill is a standard modular architecture pattern.
[OBFUSCATION]: The content is provided in clear, human-readable Markdown with no hidden characters, Base64 encoding, or homoglyph substitutions.

draft-outreach