researching-with-deepwiki

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEDATA_EXFILTRATIONEXTERNAL_DOWNLOADSPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • Data Exposure & Exfiltration (LOW): The script scripts/verify.py accesses ~/.claude/settings.json and other configuration paths to verify the MCP server setup. While these files may contain sensitive credentials, the script only performs local key-presence checks and does not exfiltrate any data.
  • Unverifiable Dependencies & Remote Code Execution (LOW): The skill configures the agent to use external third-party MCP servers at deepwiki.com and devin.ai. These are non-trusted external dependencies that handle the skill's core logic and process user queries remotely.
  • Command Execution (LOW): The SKILL.md file provides instructions for users to execute claude mcp add to modify their agent's configuration. This is a standard procedure for MCP server integration.
  • Indirect Prompt Injection (LOW): The skill analyzes untrusted third-party repositories, which is a known attack surface. A malicious repository could contain instructions in source code or README files designed to influence agent behavior. Evidence Chain: 1. Ingestion points: External code content fetched via DeepWiki MCP (referenced in SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Architecture analysis and code explanation capabilities (referenced in SKILL.md). 4. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:43 PM