The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands to extract configuration from local files and perform network operations.
It utilizes python3 -c to parse a configuration file located at ~/.gooseworks/credentials.json to set environment variables.
It uses curl to interact with the Orthogonal and Gooseworks APIs.
[INDIRECT_PROMPT_INJECTION]: The skill retrieves data from external LinkedIn profiles, company pages, and posts, which could contain malicious instructions designed to manipulate the agent.
Ingestion points: External data scraped from linkedin.com via the Scrape Creators API.
Boundary markers: None provided in the skill instructions to delimit untrusted data or instruct the agent to ignore embedded instructions.
Capability inventory: The skill has the ability to execute shell commands (curl) to perform further network requests.
Sanitization: No sanitization or validation of the retrieved LinkedIn content is mentioned.

linkedin-scraper