context7
Warn
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the ctx7 package globally using npm install -g ctx7@latest or execute it directly using npx. This involves downloading and running code from the public npm registry, which is an external and unverifiable source for this specific tool.
- [COMMAND_EXECUTION]: The skill's functionality relies on executing shell commands (ctx7 library, ctx7 docs). These commands facilitate interaction with external APIs to fetch data.
- [PROMPT_INJECTION]: The skill processes untrusted technical documentation which creates an indirect prompt injection surface. 1. Ingestion points: Data from the ctx7 docs and ctx7 library commands (SKILL.md). 2. Boundary markers: No delimiters or ignore instructions are used to separate retrieved content from instructions. 3. Capability inventory: The skill executes shell commands and installs packages. 4. Sanitization: There is no evidence of filtering or validation of the retrieved content before it is processed by the agent.
Audit Metadata