The Agent Skills Directory

External Downloads (LOW): The skill performs network operations using curl to access https://context7.com. This domain is not listed in the trusted external sources or whitelisted domains, though it is used for the skill's stated purpose of fetching documentation.
Indirect Prompt Injection (LOW): The skill fetches external documentation and processes it within the agent context, creating a potential vulnerability to embedded instructions. 1. Ingestion points: Results from API calls to context7.com in SKILL.md. 2. Boundary markers: No explicit markers are used to separate untrusted documentation content from system instructions. 3. Capability inventory: Use of curl for network access and jq for data processing. 4. Sanitization: The skill does not perform any validation or sanitization on the fetched documentation text.

context7