cwicr-schedule-integrator

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE]: The skill performs local file operations, including reading CSV/Parquet files and writing Excel reports. These operations are aligned with the 'filesystem' permission declared in the configuration and are necessary for the skill's primary function of cost-schedule integration.
  • [INDIRECT_PROMPT_INJECTION]: This skill possesses an attack surface for indirect prompt injection because it processes untrusted data from external CSV files.
  • Ingestion points: The import_schedule_from_csv method in SKILL.md reads user-provided schedule and work item files.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the processing logic.
  • Capability inventory: The skill has filesystem read/write capabilities via the pandas and openpyxl libraries.
  • Sanitization: The skill relies on standard pandas.read_csv parsing and does not implement additional sanitization or validation of input strings before they are used in calculations or potentially reflected in the agent's output.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 04:27 AM