The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill fetches external documentation from the Context7 service, which could potentially contain malicious instructions intended to influence the agent's behavior.
Ingestion points: Data retrieved from the Context7 API via the query-docs and resolve-library-id tools as described in SKILL.md.
Boundary markers: The skill does not include specific boundary markers or instructions for the agent to ignore embedded commands within the fetched documentation content.
Capability inventory: The skill is designed to use fetched documentation for code generation and answering queries; however, it does not explicitly request high-privilege capabilities such as file system writes or arbitrary shell execution.
Sanitization: There are no explicit instructions for the agent to sanitize or validate the content returned from the external documentation service.
[DATA_EXFILTRATION]: The skill instructs the agent to send user-provided queries and context to an external documentation service (Context7).
Network operations: The query-docs and resolve-library-id tools perform network requests to the external Context7 API.
Detection logic: The skill passes user-defined documentation topics and library names as parameters to an external network-based tool.

cesium-context7