saas-metrics-coach

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests raw financial metrics from users and passes them as arguments to local Python scripts, creating a potential command injection surface. * Ingestion points: User-provided values for MRR, churn, customers, and costs (SKILL.md, Step 1). * Boundary markers: None present; there are no instructions to the agent to sanitize or delimit user input. * Capability inventory: Executes shell commands via python scripts/*.py using user-supplied inputs (SKILL.md, Tools section). * Sanitization: No explicit validation or filtering logic is provided to ensure the input contains only numeric data.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute local scripts (scripts/metrics_calculator.py, scripts/quick_ratio_calculator.py, scripts/unit_economics_simulator.py) via the CLI to perform core functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 06:56 AM
Security Audit — agent-trust-hub — saas-metrics-coach