neta-character

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill uses npx to download and execute the @talesofai/neta-skills package from the NPM registry. This package is the official CLI tool provided by the skill's author.
  • [COMMAND_EXECUTION]: Several commands execute shell-based operations to create (create_character), update (update_character), and query (list_my_characters) character data.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided strings for character details such as names, personas, and descriptions which are passed into shell command arguments.
  • Ingestion points: User-defined character metadata fields (name, persona, description, interests) entered via the CLI in SKILL.md.
  • Boundary markers: Command examples utilize double quotes for field values, but do not specify internal validation to prevent command injection characters.
  • Capability inventory: Employs npx to run character management scripts across all documented workflows.
  • Sanitization: No specific sanitization logic is implemented in the skill instructions; it relies on the execution environment or the agent to handle string escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 08:27 AM
Security Audit — agent-trust-hub — neta-character