The Agent Skills Directory

[DATA_EXPOSURE]: The skill retrieves API keys from ~/.gooseworks/credentials.json. This file is specific to the vendor's infrastructure and is used for authenticating requests to its own services.
[COMMAND_EXECUTION]: Shell commands including curl and python3 are used to perform network requests and parse configuration data. These operations are directed at the vendor's own API endpoint (api.gooseworks.ai).
[INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources, including web scraping results, which could contain malicious instructions.
Ingestion points: Data is received from the brand-dev, fiber, and scrapegraph APIs as described in SKILL.md.
Boundary markers: The skill does not implement specific delimiters or instructions to ignore embedded commands in the retrieved data.
Capability inventory: The agent has capabilities for network operations (curl) and local data processing.
Sanitization: There is no explicit sanitization or validation of the external content before it is presented to the agent context.

company-intel