feature-branch

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands using the Bash tool to interact with git and the GitHub CLI (gh).
  • Evidence: The instructions in SKILL.md specify the use of gh issue view, gh issue list, git fetch, and git checkout to manage feature branches.
  • [PROMPT_INJECTION]: The skill is vulnerable to Indirect Prompt Injection (Category 8) because it processes untrusted data from external GitHub issues.
  • Ingestion points: Untrusted data enters the context through the gh issue view and gh issue list commands used in Step 1 of SKILL.md.
  • Boundary markers: Absent. The skill does not use delimiters or specific instructions to isolate or ignore potentially malicious content within the fetched issue data.
  • Capability inventory: The skill has the capability to execute commands via the Bash tool, including branch creation and checkout operations based on issue summaries.
  • Sanitization: Absent. Although the instructions request kebab-case formatting for branch names, there is no programmatic sanitization or validation of the external issue content before it is used.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 04:06 AM