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

openagent

Fail

Audited by Gen Agent Trust Hub on Oct 15, 2026

Risk Level: HIGHPRIVILEGE_ESCALATIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [PRIVILEGE_ESCALATION]: The skill instructs the agent to execute the sudo 5dive agent import command to provision new teammates. Running commands with root privileges poses a significant security risk to the host environment if the agent's instructions are compromised.
  • [COMMAND_EXECUTION]: The skill makes extensive use of shell commands through npx and the 5dive CLI to perform validation, rarity tier checks, and image rendering.
  • [EXTERNAL_DOWNLOADS]: The skill uses curl to fetch images from pollinations.ai, which is a well-known service for text-to-image generation. It also downloads assets and code from the NPM registry via npx and references repositories under the 5dive-ai organization on GitHub.
  • [REMOTE_CODE_EXECUTION]: The skill repeatedly calls npx @5dive/openagent@0.34.0, which downloads and executes the package from the NPM registry at runtime. While these are vendor-provided resources from the skill's author, the execution of remote scripts is a critical attack vector.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from user-supplied <id>.persona.yaml files.
  • Ingestion points: Multiple commands (validate, tier, card, import) read data from the persona YAML file.
  • Boundary markers: The skill relies on internal schema validation via the validate command but does not mention explicit delimiters to prevent instructions within the YAML from affecting the agent's behavior during rendering or provisioning.
  • Capability inventory: The agent can execute arbitrary shell commands (via npx), perform network operations (via curl), and provision system agents (via sudo 5dive agent import).
  • Sanitization: The skill performs schema validation (additionalProperties: false) to ensure data conforms to expected fields.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Oct 15, 2026, 02:17 PM