fleetops
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
fleetopsCLI tool to interact with a local SQLite database for fleet state and journal management. - Evidence: Found in
SKILL.mdandreferences/tool-reference.mdwhich detail verbs likejournal addandshow-state. - [EXTERNAL_DOWNLOADS]: The documentation references the
servitorrepository, maintained by the vendor, for the installation of thefleetopsbinary. - Evidence:
README.mdandreferences/tool-reference.mdmention 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, andfleetops journal showinSKILL.md. - Boundary markers: Not explicitly provided in the instructions.
- Capability inventory: Agent can execute shell commands via
fleetopsand read/write local files. - Sanitization: Not specified in the skill instructions.
Audit Metadata