The Agent Skills Directory

[SAFE]: The skill is composed exclusively of markdown files providing instructions and reference data for advertising audits. It does not include any executable code, shell scripts, or external dependencies.
[PROMPT_INJECTION]: Instructions are focused on performance analysis and adhere to standard professional guidelines. No attempts to bypass safety filters or override system instructions were detected.
[DATA_EXFILTRATION]: No network operations, API calls, or sensitive file access patterns are present. The skill does not request or handle credentials.
[OBFUSCATION]: Analysis for Base64, zero-width characters, homoglyphs, and hidden text patterns returned no findings. All content is in plain text.
[INDIRECT_PROMPT_INJECTION]: While the skill processes user-supplied ad campaign data (a potential ingestion surface), it lacks any executable capabilities (no file-write, no network access, no subprocess calls) that could be exploited via malicious data input.
[DYNAMIC_CONTEXT_INJECTION]: No use of the dynamic shell execution syntax was found in the documentation.

ads-audit