The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the @useclawlink/cli tool via npx to interact with the Google Ads API. This involves the agent executing shell commands to search, retrieve, and mutate advertising data.
[EXTERNAL_DOWNLOADS]: The skill initiates downloads of the @useclawlink/cli package from the NPM registry at runtime using npx. This is the intended delivery mechanism for the integration tool provided by the skill author.
[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests data from external Google Ads account resources.
Ingestion points: Data enters the agent's context through actions such as googleads_get_campaign_by_id, googleads_get_campaign_by_name, and GAQL queries via googleads_search_stream_gaql.
Boundary markers: There are no explicit boundary markers or delimiters defined to separate untrusted external data from the agent's instructions.
Capability inventory: The skill provides capabilities to write data to the external service, including googleads_mutate_campaigns, googleads_mutate_ad_groups, and googleads_create_customer_list.
Sanitization: There is no evidence of sanitization, filtering, or validation of the retrieved API data before it is processed by the agent.

google-ads