The Agent Skills Directory

[DATA_EXFILTRATION]: The skill reads the user's API key and base URL from ~/.gooseworks/credentials.json using a Python one-liner. This is standard configuration management for the gooseworks-ai ecosystem and the credentials are used solely for authenticating requests to the vendor's API.
[COMMAND_EXECUTION]: The skill utilizes curl for API requests and python3 -c for parsing the local JSON credential file. These operations are limited to setup and communication with the designated API endpoints.
[EXTERNAL_DOWNLOADS]: The skill fetches data from api.gooseworks.ai, which acts as a proxy to market research services like Apollo and Fiber. These interactions are legitimate for the skill's stated purpose of market analysis.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes external data from third-party APIs.
Ingestion points: API responses from the orthogonal/run, company-search, and people-search endpoints contain untrusted data from the web.
Boundary markers: None; the skill does not use specific delimiters to wrap the external API content.
Capability inventory: The skill includes network access via curl but no file system modification or arbitrary command execution capabilities.
Sanitization: No sanitization or filtering of the API output is performed before it is processed by the agent.

market-research