The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands (curl and jq) to interact with the DeepWiki API for fetching and parsing repository data.
[EXTERNAL_DOWNLOADS]: Fetches documentation data, repository structures, and AI-generated responses from the remote endpoint api.deepwiki.com.
[DATA_EXFILTRATION]: Executes network operations to a non-whitelisted domain (api.deepwiki.com). While the documented usage focuses on public repository data, the capability to send requests to an external third-party service is inherently present.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes content from an external source that may contain untrusted data or instructions.
Ingestion points: API responses from https://api.deepwiki.com containing documentation contents and AI-generated answers.
Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the API output as untrusted content.
Capability inventory: The skill utilizes shell-based tools (curl, jq) which are executed as subprocesses.
Sanitization: There is no evidence of sanitization, filtering, or validation of the content retrieved from the API before it is processed by the agent.

deepwiki-api