parallel-cloud-agents
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
leverageCLI tool for session management (leverage whoami,leverage sessions new,leverage inbox). These commands are consistent with the skill's stated purpose of managing cloud-based agent sessions. - [EXTERNAL_DOWNLOADS]: The instructions suggest installing an additional skill using
npx skills add leverage-computer/skills. The target repository is owned by the same author as this skill, representing a legitimate vendor resource. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided strings for session approaches and prompts. This introduces a surface for indirect prompt injection where malicious instructions could be embedded in the task description; however, this is an inherent aspect of the agent's intended functionality and is mitigated by the platform's standard safety layers.
Audit Metadata