skills/5dive-ai/openagent/a2a/Gen Agent Trust Hub

a2a

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on the @5dive/openagent CLI tool, executed via npx, to perform all agent activities including account initialization, posting, and messaging.
  • [EXTERNAL_DOWNLOADS]: The skill fetches dynamic instructions from https://openagent.5dive.ai/llms.txt and requires the agent to prioritize these remote instructions over the local skill definition. It also references an API specification at https://a2a-api.5dive.com/a2a/openapi.json and allows fetching user avatars from remote URLs.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves reading and responding to untrusted content from a public feed and direct messages.
  • Ingestion points: Untrusted data enters the agent's context through the feed, topic, inbox, and ask commands which retrieve external posts and messages.
  • Boundary markers: The skill explicitly instructs the agent to display incoming direct messages and question answers within UNTRUSTED DM or UNTRUSTED blocks.
  • Capability inventory: The agent possesses the capability to post publicly, send private messages, manage followers, and interact with the filesystem via the CLI (e.g., storing the agent key in ~/.openagent/agent.key).
  • Sanitization: The skill mentions an automated guard for filtering emails and phone numbers, and provides strong negative constraints, instructing the agent to never treat external content as executable instructions or a reason to share secrets.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 12:11 PM