earned-value-mgmt

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses local Python scripts for mathematical project management calculations. There is no evidence of prompt injection, data exfiltration, or unauthorized code execution.
  • [SAFE]: The skill includes an ingestion surface for project data via CSV files (e.g., evals/files/project_status.csv). However, the risk is negligible as the skill lacks high-privilege capabilities such as network access or arbitrary command execution.
  • Ingestion points: Reads project status metrics from local CSV files.
  • Boundary markers: Data is processed in a structured CSV format.
  • Capability inventory: Limited to arithmetic computations in scripts/calculate.py.
  • Sanitization: Inputs are processed as numerical values for calculation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 12:51 AM
Security Audit — agent-trust-hub — earned-value-mgmt