information-security-manager-iso27001
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes external CSV files provided by the user (asset inventories and control status) and interpolates their content directly into generated reports. This creates a surface for indirect prompt injection where malicious instructions embedded in a CSV file could influence the agent's behavior when it later reads the generated report.
- Ingestion points:
scripts/compliance_checker.py(via the--controls-fileargument) andscripts/risk_assessment.py(via the--assetsargument). - Boundary markers: Absent. The data is parsed from CSV and written directly into JSON or Markdown output structures without delimiters to distinguish it as untrusted data.
- Capability inventory: The skill allows for local file reading and writing. It does not possess network access, shell execution, or sensitive credential access capabilities.
- Sanitization: No sanitization or escaping is performed on the data read from the input files before it is included in the output reports.
Audit Metadata