mfg-predictive-maintenance

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external sensor data and equipment descriptions provided by users to generate maintenance plans. This creates a surface for indirect prompt injection where malicious instructions could be embedded in the data processed by the agent.
  • Ingestion points: The agent processes equipment names, failure frequencies, and sensor data values as defined in SKILL.md and demonstrated in examples/sample_scenario.md.
  • Boundary markers: The instructions do not specify any delimiters or boundary markers to separate user-provided data from agent instructions.
  • Capability inventory: Analysis of all files shows no subprocess calls, file-write operations, or network requests are defined within the skill's operational instructions.
  • Sanitization: There are no instructions provided for the agent to sanitize or validate external content before processing it into the final output report.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 02:06 PM
Security Audit — agent-trust-hub — mfg-predictive-maintenance