The Agent Skills Directory

[NO_CODE]: The skill is composed entirely of markdown instructions and metadata. It does not include any scripts, executables, or automated code snippets that could pose a security risk. All operations described are manual verification steps to be performed via conversation with the user.
[PROMPT_INJECTION]: The instructions are focused on guiding the agent through a specific audit workflow. There are no attempts to bypass safety filters or override system-level instructions.
[DATA_EXFILTRATION]: No network-capable tools or exfiltration patterns were detected. The skill processes data provided by the user within the context of an audit and does not send data to external servers.
[INDIRECT_PROMPT_INJECTION]: While the skill's purpose is to analyze data from external systems (ad platform UIs, payloads, CRM records), it has no capabilities (e.g., file system writes, subprocess execution) that could be exploited if malicious content were embedded in those data sources. The analysis is limited to technical verification of IDs, statuses, and values.
[TRUSTED_VENDOR_RESOURCES]: The skill references several other modules by the same author (e.g., mbfinotti/advertising-skills@ad-attribution-gap). These are internal references to the vendor's own suite of tools and are handled safely.

ad-conversion-tracking