Skills
skills/asyncfuncai/grok-wiki/grok-wiki-cli/Gen Agent Trust Hub

grok-wiki-cli

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the grok-wiki CLI and the bun runtime to perform repository analysis, manage local wikis, and run test suites.
  • [EXTERNAL_DOWNLOADS]: The skill fetches data from GitHub repositories when provided with repository shorthands or URLs for wiki generation and analysis.
  • [PROMPT_INJECTION]: The skill processes untrusted codebase content during wiki generation and querying, creating a surface for indirect prompt injection where instructions embedded in a repository could influence the agent's behavior.
  • Ingestion points: Repository files accessed via local paths or GitHub URLs in grok-wiki generate and ask commands.
  • Boundary markers: The skill documentation does not specify the use of delimiters or ignore-instructions logic for ingested content.
  • Capability inventory: Executes local commands via the grok-wiki CLI and bun runtime.
  • Sanitization: No specific content sanitization or validation steps are outlined for the processed codebase data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 02:51 PM
Security Audit — agent-trust-hub — grok-wiki-cli