spool

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: Accesses potentially sensitive system data through spool file content retrieval.
  • The read_spooled_file_data tool in tools/spool.yaml uses the SYSTOOLS.SPOOLED_FILE_DATA table function to extract raw text lines from IBM i spooled files. Spooled files are a common source of sensitive business reports, system logs, and transaction details.
  • The database connection configuration in tools/spool.yaml specifies ignore-unauthorized: true, which disables SSL certificate verification and could expose data to man-in-the-middle attacks in insecure environments.
  • [PROMPT_INJECTION]: Potential for indirect prompt injection when processing data from external spool files.
  • Ingestion points: The read_spooled_file_data tool (defined in tools/spool.yaml) reads untrusted text data from the system into the agent's context.
  • Boundary markers: The skill does not implement boundary markers or instructions to isolate the retrieved data from the agent's control flow.
  • Capability inventory: The skill provides access to system management tools and arbitrary SQL execution via the ibmi CLI as documented in SKILL.md.
  • Sanitization: There is no evidence of filtering or sanitizing the text content of spooled files before presentation to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 02:34 PM