incu-way-threat-model

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands to manage branches and worktrees within the local repository environment.\n
  • Execution of git switch, git pull, and git worktree add to create isolated environments for threat modeling.\n
  • Uses branch naming patterns like assess/threat-{slug} based on user-provided feature names.\n- [INDIRECT_PROMPT_INJECTION]: The skill analyzes external project documents, creating an attack surface for instructions embedded in those files.\n
  • Ingestion points: Processes content from PRD/PLAN, docs/architecture/, CLAUDE.md, and VALIDATION.md.\n
  • Boundary markers: No delimiters or explicit warnings are used to prevent the agent from following instructions embedded in the source documents.\n
  • Capability inventory: The agent can execute git commands and write to the local filesystem.\n
  • Sanitization: Input data is not sanitized or filtered before being processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 01:49 PM
Security Audit — agent-trust-hub — incu-way-threat-model