isms-audit-expert
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of documentation and a local Python script designed for ISO 27001 audit management. All operations are confined to the local environment and utilize standard libraries.- [INDIRECT_PROMPT_INJECTION]: The skill contains a utility for processing external data, which constitutes a potential attack surface.
- Ingestion points: The script
scripts/isms_audit_scheduler.pyreads control data from external CSV files provided via the--controlscommand-line argument. - Boundary markers: Absent. The script processes input data without specific delimiters or instructions to ignore embedded commands.
- Capability inventory: The script performs file read/write operations on the local filesystem via the standard Python
open()function; no network or subprocess capabilities are present. - Sanitization: Absent. Data from the CSV (e.g., control names and IDs) is interpolated directly into the generated JSON or Markdown output.
Audit Metadata