What the developer wrote
Authored by Felix
ci: bump security review ci model to opus 5
Bump the LLM used by the security review CI script from Claude Opus 4.8 to Claude Opus 5
What changed, and why it matters
This commit simply changes the version string of an AI model used by an internal continuous-integration (CI) security-review script. It does not modify Electrum wallet code, cryptography, networking, or any user-facing behavior. There is no indication this introduces or fixes a security vulnerability.
No security action required. Treat as routine CI maintenance.
Security signals we found
No strong security signals were identified.
Evidence from the diff
The diff updates one constant in contrib/ci/claude_security_review.py from CLAUDE_MODEL = “claude-opus-4-8” to “claude-opus-5”. This is a CI tooling-only change affecting which large language model is invoked for an automated security review helper. No application logic, dependencies, permissions, or interfaces are altered.
Changed components
contrib/ci/claude_security_review.pyInspect captured patch +1 / −1
diff --git a/contrib/ci/claude_security_review.py b/contrib/ci/claude_security_review.py
index 0982656..38a08a3 100644
--- a/contrib/ci/claude_security_review.py
+++ b/contrib/ci/claude_security_review.py
@@ -37,7 +37,7 @@ PROMPT_FILE = os.path.join(SCRIPT_DIR, "security_review_prompt.md")
MAX_DIFF_CHARS = 800_000
CLAUDE_TIMEOUT_SECONDS = 60 * 60
-CLAUDE_MODEL = "claude-opus-4-8"
+CLAUDE_MODEL = "claude-opus-5"
CLAUDE_EFFORT = "max"
VERDICT_PASS = "PASS"
Why this scored 15/100
Community notes
Notes can correct, qualify, or add evidence to the AI analysis. Every note shown here has been validated by a human moderator.
The AI analysis stands alone for now. Submit a note if you can add evidence or important context.