find-docs
Warn
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: MEDIUMREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill instructs the agent to use
npx ctx7@latestto execute documentation lookups. This method dynamically downloads and runs the latest version of a package from the public NPM registry at runtime, which bypasses version pinning and creates a supply chain risk where the tool could be replaced by a malicious version without warning. - [COMMAND_EXECUTION]: The skill requires the execution of multiple shell commands including
npx,npm install -g, andexportto configure and run the documentation tool. - [EXTERNAL_DOWNLOADS]: The skill fetches the
ctx7package from the NPM registry and makes network requests to the Context7 API to fetch documentation and API references. - [INDIRECT_PROMPT_INJECTION]: The skill ingests documentation and code snippets from an external service. * Ingestion points: Output from
ctx7 docscommand inSKILL.md. * Boundary markers: Absent. * Capability inventory: Shell command execution vianpxandnpminSKILL.md. * Sanitization: Absent; the skill relies on manual warnings to the agent rather than technical filtering. - [DATA_EXFILTRATION]: Search queries are sent to the external Context7 API. While the skill warns against including secrets, user-provided intent and context is transmitted to a third-party service.
Audit Metadata