security: isolate release issue content from shell execution (#307)

docs/release-engine-spec.md

@@ -12,8 +12,8 @@ Convert one eligible Gitea issue into a tested, traceable pull request without d
 - Repository key (`owner/repo`).
 - Agent username.
 - Optional explicit issue number; otherwise deterministic queue selection.
-- Coding-agent command template.
-- Test command.
+- Coding-agent command, parsed into an argument vector.
+- Test command, parsed into an argument vector.
 - Local repository path and durable state-file path.
 
 ## State machine
@@ -39,7 +39,10 @@ Terminal failure states are `claim_failed`, `agent_failed`, `tests_failed`, and
 ## Execution
 
 - Branch format: `<agent>/<issue>-<slug>`.
-- Coding command receives issue number, title, body, repo, and branch through template fields and environment variables.
+- Coding and test commands are parsed with POSIX argument quoting and executed directly without a shell.
+- Issue number, title, body, repo, and branch are supplied to the coding agent only through `RELEASE_ISSUE_NUMBER`, `RELEASE_ISSUE_TITLE`, `RELEASE_ISSUE_BODY`, `RELEASE_REPO`, and `RELEASE_BRANCH` environment variables. Gitea-controlled content is never interpolated into executable syntax.
+- Shell operators, substitutions, and pipelines are not interpreted. Operators that are intentionally required must live in a separately reviewed wrapper script configured as the command.
+- Empty or malformed commands abort before the issue claim.
 - Non-zero coding-agent exit blocks tests and PR creation.
 - Tests run using the configured command; stdout/stderr and exit code become evidence.