Skills
skills/jjenzz/agent-skills/vertical-slice-delivery/Gen Agent Trust Hub

vertical-slice-delivery

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses git commands for workflow automation and repository management. AGENTS.md defines command templates for staging and committing changes (git add, git commit, git restore). deliver/AGENTS.md includes a shell command chain to resolve the default branch using git symbolic-ref and sed.
  • [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection due to its core function of processing external data. Ingestion points: review/AGENTS.md is instructed to inspect staged and unstaged code changes, and deliver/AGENTS.md is instructed to review output from git log. Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the files or logs being processed. Capability inventory: The agent has shell access for executing git commands as specified in AGENTS.md and deliver/AGENTS.md. Sanitization: The skill does not define any sanitization or validation procedures for the workspace content it analyzes.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 12:41 AM