finops-manager

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is primarily a documentation and routing layer designed to maintain compatibility with legacy prompts while enforcing modern operational standards. It does not contain malicious code or instructions.\n- [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface but explicitly provides defensive instructions. Evidence Chain:\n
    1. Ingestion points: Web content and external data via BrowserOS (SKILL.md).\n
    1. Boundary markers: None specific, but mandates redaction of secrets before sharing context.\n
    1. Capability inventory: ExecutionProxy for command execution, MemoryStore for persistent file writes to Obsidian docs, and IssueTracker (SKILL.md).\n
    1. Sanitization: Mandatory redaction of secrets/PII from external content (SKILL.md).\n- [COMMAND_EXECUTION]: The skill references an execution proxy (rtk) for running terminal commands like npm tests. These are restricted to a deterministic testing environment (Unit, Contract, E2E) as part of a formal development lifecycle and do not represent unauthorized command execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 07:36 AM
Security Audit — agent-trust-hub — finops-manager