The Agent Skills Directory

[COMMAND_EXECUTION]: The skill requires the agent to execute local Python scripts (scripts/cli.py) to interact with the Apify API and manage the local cache database.
[EXTERNAL_DOWNLOADS]: The skill connects to Apify's official API endpoints (api.apify.com) to retrieve LinkedIn data. This is a well-known service and the primary purpose of the skill.
[INDIRECT_PROMPT_INJECTION]: As the skill ingests and processes untrusted data from external LinkedIn profiles and posts, it is theoretically susceptible to indirect prompt injection.
Ingestion points: scripts/apify_client.py retrieves data from the Apify REST API.
Boundary markers: SKILL.md contains explicit instructions to limit the amount of data passed back to the agent transcript and to avoid wholesale profile dumps.
Capability inventory: The skill has the ability to read/write to a local SQLite database and make network requests to a specific API.
Sanitization: scripts/extract.py provides field extraction and summarization, converting raw API responses into structured JSON results.
[CREDENTIALS_SAFE]: The skill strictly manages the Apify API token using the APIFY_API_TOKEN environment variable and includes logic in scripts/apify_client.py to redact the token from error messages and logs.

linkedin-enrichment