information-security-manager-iso27001

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates the execution of local Python tools (scripts/risk_assessment.py and scripts/compliance_checker.py) to generate risk registers and gap analysis reports. These scripts operate on local files and user-defined scopes.
  • [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it ingests untrusted external data into the agent's reasoning context.
  • Ingestion points: Data is read from user-provided files such as assets.csv and controls.csv, as well as string inputs for the --scope parameter.
  • Boundary markers: There are no documented delimiters or instructions to ignore embedded commands within the external data ingested by the scripts.
  • Capability inventory: The skill has the capability to write files to the local file system (using the --output flag) and execute script logic based on input data.
  • Sanitization: The skill documentation does not mention any validation, escaping, or filtering of content provided in the CSV files or scope definitions before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 08:05 PM
Security Audit — agent-trust-hub — information-security-manager-iso27001