creating-mcp-servers
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch technical documentation from
gofastmcp.comusing theweb_fetchtool. This external site is used as the authoritative source for the FastMCP framework documentation. - [REMOTE_CODE_EXECUTION]: The skill includes a pattern in
references/MANDATORY_PATTERNS.mdfor installing theuvpackage manager via a remote script (curl | sh) fromastral.sh. This source is the official domain of a well-known software company, Astral. - [COMMAND_EXECUTION]: The skill instructions in
SKILL.mdrequire the execution of the local scriptscripts/create_mcpb.pyand standard system commands likezipto package server files into bundles. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data fetched via
web_fetchfromgofastmcp.comto guide server construction. - Ingestion points: Documentation URLs indexed in
references/LLMS_TXT.md. - Boundary markers: None; the skill does not specify delimiters for external content.
- Capability inventory: File system writes (bundling), execution of
scripts/create_mcpb.py, and suggested patterns forsubprocess.runandsqlite3execution. - Sanitization: None; fetched content is applied directly to implementation phases.
- [DYNAMIC_EXECUTION]: The skill provides implementation templates in
references/GATEWAY_PATTERNS.mdthat utilize dynamic execution techniques. - The 'Skills Gateway' pattern uses
subprocess.runto execute Python scripts found in local directories such as~/.claude/skills. - The 'Query Gateway' pattern suggests a database interface using f-string interpolation for SQL queries, which is a vulnerable pattern compared to standard parameterized queries.
Audit Metadata