maintainx-core-workflow-a

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the MaintainX API, such as work order titles, descriptions, and user roles, which could contain malicious instructions if the source account is compromised or contains untrusted content.
  • Ingestion points: Data is retrieved via client.getWorkOrders, client.getWorkOrder, and client.getUsers as seen in SKILL.md and references/implementation-guide.md.
  • Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are used when processing API-returned strings.
  • Capability inventory: The skill is configured with Write, Edit, and Bash capabilities, which could be targeted if an injection occurs.
  • Sanitization: The provided code examples do not demonstrate validation or escaping of external content before logging or processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:46 AM
Security Audit — agent-trust-hub — maintainx-core-workflow-a