cost-control-master

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill consists entirely of instructional text and templates for financial reporting.
  • [DATA_EXPOSURE]: The skill references reading ../../CLAUDE.md to retrieve scenario-level configurations. While this uses directory traversal, it is restricted to a specific configuration file common in agentic environments and does not attempt to exfiltrate data.
  • [COMMAND_EXECUTION]: The skill describes a workflow involving other skills (e.g., standard-cost-variance) but does not invoke shell commands, subprocesses, or arbitrary system calls.
  • [PROMPT_INJECTION]: The instructions focus on structured financial analysis and do not contain attempts to override system prompts or bypass safety filters.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 02:25 AM
Security Audit — agent-trust-hub — cost-control-master