Skills
skills/aradotso/mcp-skills/ask-expert-consult-mcp-wisdom-cascade/Gen Agent Trust Hub

ask-expert-consult-mcp-wisdom-cascade

Warn

Audited by Gen Agent Trust Hub on Jun 30, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill's setup instructions require cloning a repository from an external source (https://github.com/pakgik01/ask-expert-consult-mcp.git) that is not identified as a trusted organization or well-known service.
  • [REMOTE_CODE_EXECUTION]: The installation procedure involves running npm install or pip install on the cloned repository, followed by executing the server using node or python. This pattern results in the execution of third-party code on the host system.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its core functionality of processing external data.
  • Ingestion points: The ask_expert and enrich_context tools ingest untrusted data via the question and code_snippet parameters defined in SKILL.md.
  • Boundary markers: There are no defined delimiters or instructions provided to the agent to ignore potentially malicious instructions embedded within the user-provided code snippets or questions.
  • Capability inventory: The skill possesses the capability to perform network requests to external AI models (OpenRouter) and read from a local knowledge cache (wisdom_cache.db).
  • Sanitization: No input sanitization or validation mechanisms are described for the data being interpolated into the expert consultation prompts.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 30, 2026, 07:37 PM
Security Audit — agent-trust-hub — ask-expert-consult-mcp-wisdom-cascade