skills/endlessblink/flow-state/next/Gen Agent Trust Hub

next

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local TypeScript scripts (get-tasks.ts, show-task.ts) using npx tsx within the tools/task-picker-v2 directory. These commands are used to sort, filter, and display task information.- [SAFE]: The skill interacts with local project files like MASTER_PLAN.md and uses git status for context. This data access is part of the core functionality and does not target sensitive system credentials or files. While the ingestion of data from MASTER_PLAN.md represents a surface for indirect prompt injection, it is considered safe in this context. 1. Ingestion points: MASTER_PLAN.md via get-tasks.ts. 2. Boundary markers: None. 3. Capability inventory: Subprocess calls (npx tsx) and workflow triggers (/start-dev). 4. Sanitization: None.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 01:14 AM
Security Audit — agent-trust-hub — next