The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands via the ctx7 CLI. User-provided parameters for library names and queries are interpolated directly into these commands without explicit sanitization, which could lead to command injection if malicious characters are included.
[EXTERNAL_DOWNLOADS]: The skill requires the use of the ctx7 package from the NPM registry, recommending either global installation or direct execution via npx. This involves downloading and executing code from a source not identified as a trusted vendor.
[PROMPT_INJECTION]: The skill processes content from the external Context7 documentation service, which is used for answering questions and generating code, presenting an indirect prompt injection surface. (1) Ingestion points: Output from ctx7 library and ctx7 docs (SKILL.md). (2) Boundary markers: Absent; no delimiters are used to separate external data from instructions. (3) Capability inventory: Execution of CLI commands and code generation based on documentation. (4) Sanitization: Absent; no validation or filtering of fetched content is performed.

find-docs