Skills
Navigate
skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/5000-projects-analysis/Gen Agent Trust Hub

5000-projects-analysis

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data which serves as a potential attack surface for indirect prompt injection.
  • Ingestion points: The load_projects method in SKILL.md reads all .xlsx files from a user-provided directory path.
  • Boundary markers: The skill does not employ specific delimiters or instructions to ignore potential natural language commands embedded within the Excel data.
  • Capability inventory: The skill utilizes filesystem permissions to read project data and write visualization reports (generate_report).
  • Sanitization: Data is loaded directly into pandas DataFrames without sanitizing or filtering cell content for instruction-like strings.
  • [COMMAND_EXECUTION]: The skill includes Python code that interacts with the local filesystem to perform its analysis tasks.
  • The BIMProjectAnalyzer class utilizes pathlib for file system navigation and pandas.read_excel for data ingestion.
  • The generate_report method uses matplotlib to save graphical analysis reports to the local disk.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 01:08 AM