The Agent Skills Directory

[SAFE]: No security issues or malicious patterns were identified during the analysis of the skill files.
[PROMPT_INJECTION]: No attempts to override agent behavior, bypass safety guardrails, or extract system prompts were detected in the instructions.
[DATA_EXFILTRATION]: No hardcoded credentials, sensitive file access (e.g., .ssh, .aws), or unauthorized network operations were found. Tool integrations mentioned (HubSpot, Salesforce, Zapier) are standard industry services and are referenced via internal documentation.
[REMOTE_CODE_EXECUTION]: The skill does not perform any remote script downloads, piped shell execution (curl|bash), or unverifiable package installations.
[COMMAND_EXECUTION]: No shell command execution patterns or dynamic context injection (!command) were found in the skill definitions.
[OBFUSCATION]: All content is in plain text. No Base64, zero-width characters, homoglyphs, or other obfuscation techniques were identified.

revops