The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources which could potentially contain malicious instructions intended to influence the agent's behavior.
Ingestion points: The skill reads target roles from context files located at claude-code-gtm/context/{company}_context.md and accepts free-form user input for role definitions.
Boundary markers: There are no specific delimiters or instructions defined to prevent the agent from obeying instructions that might be embedded within the context files.
Capability inventory: The skill has the ability to write files to the local system (claude-code-gtm/csv/input/{campaign}/people_linkedin.csv) and delegates complex API operations (column creation, data enrichment, data fetching) to the extruct-api skill.
Sanitization: The instructions do not specify any validation or sanitization of the role strings fetched from the ICP context files before they are passed to the search tool.

people-search