pp-agentpool

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the agentpool-pp-cli tool using npx from the @mvanhorn NPM namespace and go install from the github.com/mvanhorn repository. These resources are verified as belonging to the skill author.
  • [COMMAND_EXECUTION]: The skill is designed to execute the agentpool-pp-cli binary. It includes an exec command that permits passing arbitrary arguments to the underlying agentpool binary, which is the intended purpose of this developer tool.
  • [PROMPT_INJECTION]: The agentpool-pp-cli skill command retrieves agent guidance text that is processed by the AI. This represents an indirect prompt injection surface as the agent is instructed to follow the guidance retrieved from the tool.
  • Ingestion points: Output from the agentpool-pp-cli skill command in SKILL.md.
  • Boundary markers: Not explicitly defined in the skill instructions; relies on the agent's internal handling of tool output.
  • Capability inventory: The skill has the ability to execute shell commands via the CLI wrapper.
  • Sanitization: No sanitization or filtering of the retrieved guidance is described in the skill metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 06:51 PM
Security Audit — agent-trust-hub — pp-agentpool