neta-community

Pass

Audited by Gen Agent Trust Hub on Oct 5, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill instructs the agent to use npx -y @talesofai/neta-skills@latest. This execution pattern downloads and runs code from the NPM registry at runtime. Using the @latest version tag is a security risk as the remote package content can be updated without notice, potentially altering the tool's behavior.
  • [EXTERNAL_DOWNLOADS]: The skill requires downloading the @talesofai/neta-skills package from the external NPM registry to perform its core functions.
  • [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands for API interaction and local data management, including creating directories and writing JSON files to the local file system (e.g., character_cache/ and research/).
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The skill retrieves community-generated data, including character bios, hashtag lore, and feed content, through API commands like request_character_or_elementum and get_hashtag_info.
  • Boundary markers: There are no explicit delimiters or boundary markers defined in the instructions to help the agent distinguish between data and potentially malicious embedded instructions.
  • Capability inventory: The agent has the capability to execute shell commands through npx and perform file system read/write operations.
  • Sanitization: There is no evidence of sanitization, filtering, or validation of the retrieved API content before it is ingested into the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 5, 2026, 09:53 AM