finishing-a-development-branch

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The skill executes standard development environment commands (git, npm, cargo, pytest, go, gh). These operations are necessary for the primary purpose of the skill and do not target sensitive system areas.
  • [INDIRECT_PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection via maliciously crafted branch names or test suite outputs.
  • Ingestion points: Step 1 (test output) and Step 2 (git branch names) ingest external data into the agent's context.
  • Boundary markers: The skill uses markdown code blocks and specific headers to structure input and output, providing some delimitation.
  • Capability inventory: The skill can execute shell commands (git, npm, etc.), modify local files (git merges), and communicate with GitHub (gh pr create).
  • Sanitization: No explicit sanitization or escaping of branch names or test results is defined before they are interpolated into commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:49 PM