guard-mutating-tool — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited guard-mutating-tool (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Scan the current diff against the CLAUDE.md § Safety matrix (cached in references/guard-matrix.md) and emit a structured report the staff-reviewer agent can consume directly.
Parse $ARGUMENTS:
--base <ref> — base ref for the diff. Defaults to origin/main.Validate the base ref:
git rev-parse --verify "${BASE:-origin/main}" >/dev/null \
|| abort "Unknown base ref: $BASE" git diff --name-only "${BASE:-origin/main}"...HEAD -- 'internal/tools/*.go'Filter by basename to one of: lifecycle, files, patch_blocklist, or any *_preflight (files that implement reboot, upgrade, rollback, reset, patch_config, apply_config, or preflight helpers that gate those mutations). Exit early with verdict GO if the filtered list is empty.
references/guard-matrix.md. Itsrequired_args and default_values columns are the ground truth.
git diff "${BASE:-origin/main}"...HEAD -U3 -- <file> \
| grep -nE 'confirm|nodes|dry_run|preserve|graceful|wait'Cross-reference the hunks against the matrix row for the tool.
if !confirm / len(nodes)==0),dry_run: true → dry_run: false),through the guard check.
4b. Preflight helper check. For any *_preflight.go in the filtered set, load .claude/rules/quorum-member-counting.md and apply its invariants against the diff (dedup by member Id before counting, map[<id-type>]struct{} structure, no reliance on len(msg.GetMembers())). Flag as regression if a preflight helper is introduced or modified without the dedup pattern.
## Guard Audit — <change-id>
| tool | required_args_ok | defaults_ok | evidence | verdict |
|-------------------|------------------|-------------|-----------------------------|---------|
| talos_reboot | yes/no | yes/no | <file:line> `<quoted code>` | pass/fail |
| talos_upgrade | ... | ... | ... | ... |
| talos_rollback | ... | ... | ... | ... |
| talos_reset | ... | ... | ... | ... |
| talos_patch_config| ... | ... | ... | ... |
| talos_apply_config| ... | ... | ... | ... |
## Findings
- **<tool>.<guard>** — <pass|regress|missing>
Evidence: <file:line> `<quoted code>`
Validation: re-run `grep -nE '<pattern>' <file>` — guard still present.
## Verdict
<approved | escalate: guards regressed>Omit rows for tools whose file was not touched.
references/guard-matrix.md — guard matrix mirrored verbatim from repo-root CLAUDE.md § Safety..claude/rules/quorum-member-counting.md — preflight helper invariants (member-ID dedup, strict-majority rule).~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.