The Agent Skills Directory

PROMPT_INJECTION (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8) because it ingests untrusted data from an external API. • Ingestion points: Data is fetched via curl from fullstackrecipes.com. • Boundary markers: None; the skill provides no instructions to the agent on how to differentiate between the system prompt and instructions found within the fetched recipes. • Capability inventory: The skill description states the agent will 'follow recipes', implying it may execute actions based on the fetched data. • Sanitization: There is no visible sanitization of the fetched markdown content.
EXTERNAL_DOWNLOADS (LOW): The skill uses curl to fetch content from https://fullstackrecipes.com. This domain is not included in the pre-approved list of trusted sources, representing a dependency on an external, untrusted entity.

use-fullstackrecipes