skills/netaart/neta-skills/neta-space/Gen Agent Trust Hub

neta-space

Warn

Audited by Gen Agent Trust Hub on Oct 5, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill frequently uses npx to fetch and execute the @talesofai/neta-skills package from the NPM registry. It also includes a command to add another skill from a remote GitHub repository: npx skills add talesofai/neta-skills/skills/neta-creative.
  • [REMOTE_CODE_EXECUTION]: The instructions rely on npx -y @talesofai/neta-skills@latest, which downloads and executes remote code at runtime without user confirmation. This creates a significant supply chain dependency on the external package and the NPM registry.
  • [COMMAND_EXECUTION]: All core functionalities of the skill (listing spaces, retrieving lore, reading collections) are implemented via shell commands executed through npx.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from an external API, including worldbuilding lore and user-generated collections, which could contain malicious instructions.
  • Ingestion points: API responses containing space descriptions, lore, and collection content (found in SKILL.md).
  • Boundary markers: The skill does not provide explicit delimiters or instructions to the agent to treat the retrieved API content as untrusted data.
  • Capability inventory: The skill possesses the ability to execute shell commands via npx.
  • Sanitization: There is no evidence of sanitization or filtering of the external API content before it is presented to the agent's context.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Oct 5, 2026, 09:52 AM