The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the ctx7 command-line tool from the NPM registry using npm install -g ctx7@latest.
[REMOTE_CODE_EXECUTION]: The skill uses npx ctx7@latest, which downloads and executes code from a remote package repository at runtime.
[COMMAND_EXECUTION]: The agent is directed to execute shell commands (ctx7 library, ctx7 docs, ctx7 login) to perform searches and manage authentication.
[INDIRECT_PROMPT_INJECTION]: The skill retrieves technical documentation and code examples from external sources via the ctx7 docs command. This creates a surface for tool output poisoning where malicious instructions embedded in third-party documentation could be ingested by the agent.
Ingestion points: Documentation and code snippets returned by the ctx7 CLI tool.
Boundary markers: Absent; the skill does not specify delimiters or instructions to ignore embedded commands in the retrieved data.
Capability inventory: Shell command execution (ctx7), file writing/code generation based on documentation content.
Sanitization: Absent; the skill relies on the model's internal safety guardrails when processing external text.

context7