release
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Executes repository-local scripts (scripts/release/prepare-release-artifacts.mjs, scripts/release/publish.sh) and git commands to manage release artifacts and publishing.
- [PROMPT_INJECTION]: The skill identifies a potential surface for indirect prompt injection via user-supplied parameters.
- Ingestion points: User-provided and arguments are used to construct shell commands in SKILL.md and references/release-workflow.md.
- Boundary markers: No delimiters or warnings are used to isolate user-provided strings within command templates.
- Capability inventory: The skill uses the Bash tool to execute Node.js and shell scripts with administrative-level control over the repository state.
- Sanitization: There are no instructions for the agent to validate or escape inputs before execution, relying on the agent's internal safety logic.
Audit Metadata