neta-suggest

Pass

Audited by Gen Agent Trust Hub on Oct 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx -y to download the @talesofai/neta-skills package from the NPM registry at runtime. This dependency is not pinned to a specific version, allowing potentially unverified code to be fetched during execution. Evidence: Found throughout SKILL.md in commands like npx -y @talesofai/neta-skills@latest.
  • [REMOTE_CODE_EXECUTION]: The use of npx to fetch and immediately run a package constitutes remote code execution, as the package content is hosted externally and executed in the local environment. Evidence: Commands such as npx -y @talesofai/neta-skills@latest suggest_keywords.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands, including environment variable configuration and file system operations like writing to and reading from temporary files in /tmp. Evidence: DEBUG=* npx ... and npx ... > /tmp/categories_level1.json in the optimization and debugging sections.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data and interpolates it into shell command arguments, creating an attack surface for command injection and prompt injection.
    1. Ingestion points: User-supplied strings enter via --prefix, --keyword, and --search_keywords parameters in SKILL.md.
    2. Boundary markers: No delimiters or sanitization warnings are present to isolate user input from the command structure.
    3. Capability inventory: Subprocess execution via npx and shell redirection.
    4. Sanitization: No sanitization or escaping mechanisms are documented for the interpolated inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 5, 2026, 09:53 AM