skills/incu-tech/incuway/incu-way-po/Gen Agent Trust Hub

incu-way-po

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes Git commands to manage development isolation. It uses git switch, git pull, and git worktree add to create branches and worktrees for requirement drafting. The commands use a {slug} variable, which is constrained by the skill's defined sequential and kebab-case naming format.
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes external content, which introduces a potential surface for indirect prompt injection.
  • Ingestion points: Reads repository source code, PRD.md, CLAUDE.md, and existing files in docs/requirements/ or docs/prds/ to assess feasibility.
  • Boundary markers: The instructions do not specify explicit delimiters for separating external file content from the agent's internal instructions, relying on an analytical read-only flow.
  • Capability inventory: The skill has the capability to execute shell commands (Git) and write new requirement files (TICKET.md) to the local file system. It also includes optional integration with Jira tools.
  • Sanitization: No specific sanitization or filtering of codebase content is mentioned before it is processed by the agent.
  • [EXTERNAL_DOWNLOADS]: The skill provides optional integration with Atlassian's Jira platform for ticket synchronization. This capability is triggered only upon explicit user request and utilizes official integration tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 01:48 PM
Security Audit — agent-trust-hub — incu-way-po