skills/5dive-ai/skills/openagent/Gen Agent Trust Hub

openagent

Warn

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: MEDIUMPRIVILEGE_ESCALATIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [PRIVILEGE_ESCALATION]: The skill instructs the agent to use sudo for the 5dive agent import command to provision new agents. While this is part of the agent lifecycle management, the use of sudo involves acquiring administrative privileges.
  • [COMMAND_EXECUTION]: The skill executes multiple shell commands using the npx utility and the 5dive CLI for validating personas, rendering cards, and importing agents.
  • [EXTERNAL_DOWNLOADS]: The skill uses curl to fetch images from Pollinations.ai, an external image generation service. It also fetches the @5dive/openagent package from the npm registry using npx.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided identity data (name, role, behavior) and incorporates it into a persona file. \n
  • Ingestion points: User identity details gathered in chat are written to a <id>.persona.yaml file. \n
  • Boundary markers: Identity data is encapsulated within a structured YAML schema. \n
  • Capability inventory: The skill can execute shell commands via npx and sudo 5dive, and perform network operations via curl. \n
  • Sanitization: The skill includes instructions to validate the persona file against a schema and enforce a pattern for the identity handle.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 13, 2026, 07:13 AM
Security Audit — agent-trust-hub — openagent