lookup

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides an update action that executes a shell script (scripts/update.sh) to manage the ctx7 CLI tool. This script performs routine maintenance tasks including version verification and global package installation via npm.
  • [EXTERNAL_DOWNLOADS]: The update script retrieves reference content from the Upstash GitHub repository. These downloads originate from a well-known service and are used for drift detection against the skill's local vendor baselines.
  • [DYNAMIC_CONTEXT_INJECTION]: The SKILL.md file uses the ! command syntax to execute ctx7 --version at load time. This is a benign implementation used solely to report the current installation status of the required CLI to the agent.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes documentation from the Context7 API, creating a vulnerability surface for indirect prompt injection.
  • Ingestion points: ctx7 docs CLI command and mcp__context7__query-docs tool (SKILL.md).
  • Boundary markers: The skill instructs the agent to ground answers in retrieved content and notify the user of fallback scenarios.
  • Capability inventory: The agent possesses the capability to execute specific shell commands and use retrieved documentation for natural language generation.
  • Sanitization: No specific input sanitization or filtering of the API output is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 07:55 PM
Security Audit — agent-trust-hub — lookup