gitkkal-pr
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted data from the repository history, which could be exploited to manipulate the agent's output or command execution.
- Ingestion points: The workflow ingests
git commitmessages,git diffoutput,.github/pull_request_template.md, and localgitkkalconfiguration files (SKILL.md Workflow steps 1, 6, 7). - Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious commands embedded within the commit history or diffs (SKILL.md Workflow/Persona sections).
- Capability inventory: The skill possesses the ability to execute GitHub CLI commands (
gh pr create,gh pr edit) and push code to remote branches (git push) (SKILL.md Workflow step 8). - Sanitization: There is no requirement or evidence of sanitization or escaping for the content derived from untrusted repository data before it is interpolated into shell-executed CLI arguments (SKILL.md Workflow step 8).
Audit Metadata