The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user or agent to install an external CLI tool via NPM using npm install -g ctx7@latest or run it via npx. This package originates from an unverified source and is not part of the standard set of trusted organizations.
[COMMAND_EXECUTION]: The skill's primary functionality relies on executing shell commands, specifically ctx7 library and ctx7 docs, to interact with the Context7 documentation service.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted documentation content from an external API.
Ingestion points: Documentation and code snippets returned by the ctx7 library and ctx7 docs commands are incorporated into the agent's context (SKILL.md).
Boundary markers: There are no specific delimiters or instructions for the agent to ignore embedded commands within the fetched documentation.
Capability inventory: The skill possesses shell execution capabilities through the CLI tool integration (SKILL.md).
Sanitization: No evidence of sanitization, filtering, or validation of the external content is present in the skill's instructions.
[DATA_EXFILTRATION]: The skill performs network operations to reach the Context7 service and involves handling authentication credentials via environment variables (CONTEXT7_API_KEY) or login commands (ctx7 login). While the skill warns against including sensitive data in queries, the network-enabled CLI tool provides a mechanism for data transmission to a non-whitelisted domain.

find-docs