atxp

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches the atxp and @atxp/client packages from the public npm registry to provide CLI and programmatic functionality.
  • [COMMAND_EXECUTION]: Executes shell commands via npx to perform search and media generation tasks.
  • [REMOTE_CODE_EXECUTION]: Leverages npx to download and run the ATXP toolset directly from a remote package registry. This is the standard distribution model for the service.
  • [PROMPT_INJECTION]: Features a surface for indirect prompt injection by processing external content from web and social media searches.
  • Ingestion points: Results from npx atxp search and npx atxp x contained in SKILL.md.
  • Boundary markers: None specified to differentiate between tool output and instructions.
  • Capability inventory: Can execute CLI commands via npx and perform network requests as described in SKILL.md.
  • Sanitization: No explicit filtering or sanitization of search results is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 03:32 AM