skills/teamhelix-ai/helix/fleet/Gen Agent Trust Hub

fleet

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and summarizes session status data.
  • Ingestion points: The agent context is populated by the output of the ${CLAUDE_PLUGIN_ROOT}/bin/helix fleet status command.
  • Boundary markers: No explicit delimiters or boundary markers are defined to isolate session-supplied data (such as titles, labels, or slugs) from the agent's instructions.
  • Capability inventory: The skill is authorized to execute shell commands via the helix binary using Bash and PowerShell.
  • Sanitization: No sanitization or filtering of session-provided metadata is described before processing.
  • [COMMAND_EXECUTION]: The skill executes a vendor-provided CLI utility to manage local server state and query JSON registries.
  • Evidence: The skill calls ${CLAUDE_PLUGIN_ROOT}/bin/helix fleet up and ${CLAUDE_PLUGIN_ROOT}/bin/helix fleet status across multiple platforms.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 05:20 PM
Security Audit — agent-trust-hub — fleet