The Agent Skills Directory

[SAFE]: The skill consists entirely of Markdown, JSON, and YAML configuration files used for guiding AI agent behavior during audits of marketing materials. No malicious patterns, such as prompt injection, obfuscation, or data exfiltration, were identified.
[NO_CODE]: The skill does not contain any scripts (Python, Node.js, Shell), executables, or definitions for external tools. The absence of executable components eliminates the risk of Remote Code Execution (RCE) or local system compromise.
[DATA_EXPOSURE_AND_EXFILTRATION]: No sensitive file paths, hardcoded credentials, or network communication patterns (e.g., curl, fetch) are present in the skill files.
[INDIRECT_PROMPT_INJECTION]: While the skill is designed to process untrusted user data (such as landing pages or marketing copy for auditing), it lacks any functional capabilities (tools, file writes, or network access) that could be exploited via an injection attack. The risk is limited to the accuracy of the agent's textual output.

authority-credibility