judgment-day

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local maintenance script core/hooks/_shared/receipt-mint.js using the node runtime to generate review receipts.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it ingests and processes external code files as part of the review process.
  • Ingestion points: External code files and project scopes identified during the Skill Resolution phase.
  • Boundary markers: None explicitly defined in the instruction set to isolate or delimit untrusted external content.
  • Capability inventory: Ability to execute shell commands (node), perform memory search and save operations (mem_search, mem_save), and launch multiple autonomous sub-agents.
  • Sanitization: No evidence of sanitization, escaping, or validation of the ingested file content prior to processing by judges or the fix agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 09:56 AM
Security Audit — agent-trust-hub — judgment-day