Skills
skills/zz3310969/max-skills/mcp-us-equities-read/Gen Agent Trust Hub

mcp-us-equities-read

Fail

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill uses a high-risk installation pattern: curl -fsSL https://raw.githubusercontent.com/zz3310969/max-skills/main/scripts/install-rw.sh | bash. This allows code from an external GitHub repository to execute directly on the user's host system without prior inspection.
  • [COMMAND_EXECUTION]: Core functionality relies on executing the rw command-line tool with user-specified parameters.
  • [EXTERNAL_DOWNLOADS]: The skill configures a remote VPS endpoint using a raw IP address (113.44.56.214), bypassing DNS security and reputation systems.
  • [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection. Ingestion points: rw call tool arguments in SKILL.md. Boundary markers: JSON formatting is used for arguments, but no explicit 'ignore embedded instructions' delimiters are present. Capability inventory: Execution of the rw CLI tool. Sanitization: No sanitization or validation of user-provided fields is documented in the skill definition.
Recommendations
  • HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/zz3310969/max-skills/main/scripts/install-rw.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 10, 2026, 03:41 PM