release
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes multiple shell commands and local scripts including
git,gh,go run, andmise runto manage the release workflow. These commands are necessary for its primary purpose of repository management and software publishing. - [INDIRECT_PROMPT_INJECTION]: The skill parses output from external CLI tools (e.g., git status, GitHub CLI) to determine workflow logic, representing a standard attack surface for indirect prompt injection.
- Ingestion points: Command outputs from git, gh, and local Go-based release tools.
- Boundary markers: Absent; the skill relies on direct command output parsing.
- Capability inventory: High-privilege actions including repository tagging, artifact publishing, and workflow dispatching.
- Sanitization: No explicit sanitization or validation logic is defined for data extracted from tool outputs.
Audit Metadata