Skills
Navigate
skills/leverage-computer/skills/team-agent-skills/Gen Agent Trust Hub

team-agent-skills

Pass

Audited by Gen Agent Trust Hub on Nov 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the leverage CLI and npx to manage skills. It instructs the agent to run leverage sessions new and npx skills add leverage-computer/skills. These commands target the vendor's own platform and repositories.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it reads the content of SKILL.md files from the local filesystem (~/.claude/skills/) to publish them. This is the primary intended functionality of the skill. * Ingestion point: ~/.claude/skills/<name>/SKILL.md (SKILL.md) * Boundary markers: Absent * Capability inventory: leverage sessions new, npx skills add (SKILL.md) * Sanitization: Absent
  • [EXTERNAL_DOWNLOADS]: The skill mentions installing the leverage-cloud-agents skill from the leverage-computer/skills repository. This is a reference to the author's own official skill library.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 9, 2026, 06:41 AM