define-prioritization-framework

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-supplied data to generate prioritization rankings and executive summaries.
  • Ingestion points: The agent ingests candidate item lists (names and descriptions) and customer-research data provided by the user in the SKILL.md instructions.
  • Boundary markers: There are no explicit instructions or delimiters defined to isolate untrusted data or prevent the agent from executing instructions embedded within the inputs.
  • Capability inventory: The skill utilizes read-only tools (Read, Grep) and produces a markdown artifact. It does not have access to the network, system shell, or arbitrary file writing.
  • Sanitization: The instructions do not specify any validation or sanitization of the user-provided feature descriptions or research summaries.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 11:44 AM
Security Audit — agent-trust-hub — define-prioritization-framework