The Agent Skills Directory

[DATA_EXPOSURE]: The skill instructions read the user's API key from ~/.gooseworks/credentials.json. This is the standard local credential store for the gooseworks-ai ecosystem.
[INDIRECT_PROMPT_INJECTION]: The skill processes content from external URLs (images, receipts, and web pages), which presents a standard risk surface for instructions embedded in third-party data.
Ingestion points: External image URLs and website domains provided to the scrapegraph, riveter, and linkup API endpoints.
Boundary markers: The instructions do not specify any delimiters or safety markers to isolate retrieved data from the AI's processing logic.
Capability inventory: The skill utilizes curl for network requests and python3 for credential parsing.
Sanitization: There is no evidence of pre-processing or sanitization performed on the content fetched from external URLs before it is passed to the analysis engines.

image-analyzer