The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional Markdown files and reference documentation. No executable scripts (Python, JavaScript, Shell) or binary files are present in the skill.
[SAFE]: No external network calls, remote code download patterns, or third-party package dependencies (NPM, PyPI) are defined or utilized.
[SAFE]: The instruction to read local context files like .agents/product-marketing-context.md is a benign and standard pattern for specializing agent responses to the user's environment.
[SAFE]: A thorough scan for prompt injection, obfuscation techniques, and hardcoded credentials yielded no findings.
[SAFE]: All referenced tools (e.g., HubSpot, Salesforce, Zapier) are mentioned for guidance and documentation purposes only, with no automated implementation logic or tool definitions that could be exploited.

revops