skills/skuridin/agent-stuff/bearcli/Gen Agent Trust Hub

bearcli

Pass

Audited by Gen Agent Trust Hub on May 6, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the bearcli command-line tool to manage Bear notes. It performs standard operations like searching, reading, and editing notes, which is the primary purpose of the skill.\n- [PROMPT_INJECTION]: The skill is potentially vulnerable to indirect prompt injection because it reads note content. If a note contains malicious instructions, the agent might execute them.\n
  • Ingestion points: SKILL.md (via bearcli cat, bearcli show, and bearcli search commands)\n
  • Boundary markers: Absent\n
  • Capability inventory: Shell command execution (bearcli) across all workflows\n
  • Sanitization: Absent
Audit Metadata
Risk Level
SAFE
Analyzed
May 6, 2026, 02:37 PM
Security Audit — agent-trust-hub — bearcli