The Agent Skills Directory

[PROMPT_INJECTION]: The skill instructions do not contain any attempts to override system prompts, bypass safety filters, or use jailbreak techniques. The tone is professional and focused on advertising planning.
[DATA_EXPOSURE]: No hardcoded credentials or sensitive file paths were detected. The skill explicitly includes 'Privacy gates' in its asset files to ensure client data isolation and credential protection.
[EXTERNAL_DOWNLOADS]: The skill does not perform any external network requests or downloads from unknown sources. It references internal files for platform research.
[REMOTE_CODE_EXECUTION]: There are no scripts, package managers (npm, pip), or dynamic execution patterns (eval, exec) that could lead to remote code execution.
[COMMAND_EXECUTION]: No shell commands or subprocess calls are present in the instructions or templates.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied business context (economics, account state) to generate plans. While this is an ingestion surface, the instructions emphasize 'Evidence gates' and 'Regulatory gates' to validate inputs, and the skill lacks dangerous capabilities that could be exploited via malicious data.
[OBFUSCATION]: All content is in plain text. No Base64, hex encoding, or hidden Unicode characters were found.

ads-plan