The Agent Skills Directory

[SAFE]: The skill provides documentation and schema definitions for advertising governance tasks. No executable scripts, dangerous shell commands, or obfuscated payloads were found.
[INDIRECT_PROMPT_INJECTION]: The skill defines tasks that ingest untrusted external data, creating an attack surface for indirect prompt injection.
Ingestion points: calibrate_content (accepts url and text samples), validate_content_delivery (accepts sales_agent_url), and get_media_buy_artifacts (accepts sales_agent_url).
Boundary markers: None are explicitly defined in the task examples to isolate the external content from the agent's instructions.
Capability inventory: The skill manages property lists, campaign plans, and audit logs via API tasks; it does not perform file system operations or direct command execution.
Sanitization: The documentation does not specify sanitization or filtering protocols for the ingested content, though the primary purpose of the skill is to perform content safety checks.

adcp-governance