chore(deps): update supabase/agent-skills digest to 8331f91

[renovate]

This PR contains the following updates:

Package	Update	Change
supabase/agent-skills	digest	1207767 → 8331f91

---

Configuration

📅 Schedule: (UTC)

• Branch creation
  • Between 12:00 AM and 03:59 AM, only on Monday (* 0-3 * * 1)
• Automerge
  • At any time (no schedule defined)

🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.

♻ Rebasing: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox.

🔕 Ignore: Close this PR and you won't be reminded about this update again.

---

• If you want to rebase/retry this PR, check this box

---

This PR was generated by Mend Renovate. View the repository job log.

[toolhive-release-app]

🛡️ Skill Security Scan Results

✅ supabase

• Status: Passed
• Findings: 9
• Allowed (not blocking): 2
  • MANIFEST_MISSING_LICENSE (Allowed: supabase/agent-skills is licensed MIT at the repository root; upstream does not embed an SPDX license identifier in per-skill SKILL.md frontmatter.)
  • LLM_UNAUTHORIZED_TOOL_USE (Allowed: references/skill-feedback.md's GitHub-issue-filing workflow is gated on
    an explicit up-front user consent step ("Ask permission — Ask the user
    if they'd like to submit feedback... If they decline, move on.") before
    any draft/submit happens. This is a documented, human-in-the-loop
    feedback-reporting workflow, not a covert or unconditional external
    write. supabase/agent-skills @8331f910845103c08d51f6ca1d86ebb7d1f745e3.
    )

✅ supabase-postgres-best-practices

• Status: Passed
• Findings: 3

---

Summary: Scanned 2 skill(s), all passed security checks. ✅

[renovate]

Edited/Blocked Notification

Renovate will not automatically rebase this PR, because it does not recognize the last commit author and assumes somebody else may have edited the PR.

You can manually request rebase by checking the rebase/retry box above.

⚠️ Warning: custom changes will be lost.

[danbarr]

Pushed a follow-up commit allowlisting the `skill-security-scan` finding on `skills/supabase/spec.yaml`.

The blocking finding (`LLM_UNAUTHORIZED_TOOL_USE`, HIGH) flags a new file added upstream, `references/skill-feedback.md`, which instructs the agent to file a GitHub issue with feedback. Checked the actual file content: it's gated on an explicit up-front user consent step ("Ask permission... If they decline, move on.") before any draft/submit happens — a documented, human-in-the-loop workflow, not a covert external write. Added an allowlist entry with that justification; the four `ATR_2026_00061` "fetch" pattern matches in this same PR are below the block threshold and don't need action.