appfolio-core-workflow-b

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies an ingestion surface for potentially untrusted data through maintenance requests and resolution notes.
  • Ingestion points: The description field in Step 1 and the resolution field in Step 4 are designed to process text typically provided by tenants or vendors.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the code snippets.
  • Capability inventory: The skill is granted access to tools including Bash, Edit, and Write (SKILL.md).
  • Sanitization: The examples demonstrate direct interpolation of data into API methods without explicit validation or escaping.
  • [SAFE]: The skill references official resources from well-known and trusted vendor domains.
  • Evidence: The Resources section contains links to www.appfolio.com and engineering.appfolio.com for official API documentation and engineering guidance.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:46 AM
Security Audit — agent-trust-hub — appfolio-core-workflow-b