vexor-cli

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute the vexor binary to search and index repository files. This is the core functionality of the skill.\n- [PROMPT_INJECTION]: The skill allows the agent to ingest content from local files, which serves as a vector for indirect prompt injection if the files contain malicious instructions.\n
  • Ingestion points: File search results and matching snippets extracted from the filesystem (SKILL.md).\n
  • Boundary markers: The skill does not define specific delimiters to wrap or identify untrusted content retrieved from searches.\n
  • Capability inventory: Subprocess execution of the vexor CLI utility.\n
  • Sanitization: No sanitization or validation of the retrieved file content is performed to prevent instruction injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 05:50 PM