git-release-start

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes standard git and platform-specific commands (glab, gh) to manage branches. These operations are core to the skill's functionality.\n- [PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection by processing branch names from the repository environment.\n
  • Ingestion points: The skill reads existing branch names via git branch -r to identify naming conventions.\n
  • Boundary markers: There are no explicit markers used to separate the ingested branch name data from the instructions or commands.\n
  • Capability inventory: The agent has access to glab api, gh api, and file-writing capabilities (echo), which could be misused if a branch name contains shell-injection payloads.\n
  • Sanitization: The instructions do not specify any validation or sanitization steps for branch names before they are used in shell commands or API requests.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 04:29 AM
Security Audit — agent-trust-hub — git-release-start