The Agent Skills Directory

[SAFE]: The skill is a legitimate development tool for auditing and implementing conversion tracking stacks. All analyzed reference files provide standard, best-practice code snippets for various advertising platforms.
[DATA_EXPOSURE_AND_EXFILTRATION]: The skill correctly instructs the user to use environment variables (e.g., process.env.STRIPE_SECRET_KEY) for sensitive credentials instead of hardcoding them. It does not attempt to access sensitive local files or exfiltrate data to unauthorized domains.
[REMOTE_CODE_EXECUTION]: No remote script downloads or dynamic code execution patterns were found. The skill provides static code snippets for the user to manually integrate into their project.
[PROMPT_INJECTION]: No attempts to override agent behavior, bypass safety filters, or extract system prompts were detected in the instructions or metadata.
[OBFUSCATION]: The skill uses clear, readable Markdown and code. No Base64, zero-width characters, or other obfuscation techniques were identified.
[INDIRECT_PROMPT_INJECTION]: While the skill involves processing site code (Phase 1: Detect), it does not execute instructions found within that data. The threat surface is minimal as it primarily generates a Markdown report.

conversion-tracking