neta-community
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
@talesofai/neta-skillsCLI tool usingnpxto perform API-driven tasks such as reading collections, searching characters, and interacting with the community feed.\n- [EXTERNAL_DOWNLOADS]: The skill downloads and runs the@talesofai/neta-skillspackage from the NPM registry. This is a vendor-owned resource created by the skill author, which is required for the skill's core functionality.\n- [PROMPT_INJECTION]: The skill ingests external content from the Neta platform (e.g., character descriptions and community comments), presenting a surface for indirect prompt injection.\n - Ingestion points: Data retrieved from
read_collection(SKILL.md),get_hashtag_info(references/hashtag-research.md), andrequest_interactive_feed(references/interactive-feed.md).\n - Boundary markers: No specific delimiters or safety instructions are used to separate external platform data from the agent's internal logic.\n
- Capability inventory: The agent can execute commands and perform write operations like posting comments and following users (references/social-interactive.md).\n
- Sanitization: The instructions do not specify any validation or sanitization steps for the data fetched from the Neta API.
Audit Metadata