x-bookmarks-manager

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The scripts/setup.sh script downloads and installs the @steipete/bird package from the public npm registry to the local project environment.
  • [COMMAND_EXECUTION]: The skill executes various shell commands to manage environment setup, install Node.js dependencies, and run the bird CLI for account verification and data retrieval.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from external X bookmarks, creating an indirect prompt injection attack surface.
  • Ingestion points: Content fetched via bird bookmarks --json in the scripts/x-bookmarks script.
  • Boundary markers: Absent; the skill does not wrap the retrieved bookmark content in delimiters or provide instructions to the agent to ignore embedded commands.
  • Capability inventory: The skill can execute shell commands, manage npm packages, and write to the local file system within the .skills-data directory.
  • Sanitization: No sanitization or filtering is performed on the bookmark text before it is returned to the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 03:16 AM
Security Audit — agent-trust-hub — x-bookmarks-manager