skills/leegonzales/aiskills/fleetops/Gen Agent Trust Hub

fleetops

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the fleetops CLI tool to interact with a local SQLite database for fleet state and journal management.
  • Evidence: Found in SKILL.md and references/tool-reference.md which detail verbs like journal add and show-state.
  • [EXTERNAL_DOWNLOADS]: The documentation references the servitor repository, maintained by the vendor, for the installation of the fleetops binary.
  • Evidence: README.md and references/tool-reference.md mention the binary source.
  • [PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection by retrieving and processing data from a shared database (fleet.db) that aggregates information from various sources like 'dreams' or 'memory'.
  • Ingestion points: fleetops search-knowledge, fleetops journal tail, and fleetops journal show in SKILL.md.
  • Boundary markers: Not explicitly provided in the instructions.
  • Capability inventory: Agent can execute shell commands via fleetops and read/write local files.
  • Sanitization: Not specified in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 03:29 AM