chore(deps): update firebase/agent-skills digest to e35a2d5

[renovate]

This PR contains the following updates:

Package	Update	Change
firebase/agent-skills	digest	073edf7 → e35a2d5

---

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

✅ firebase-ai-logic-basics

• Status: Passed
• Findings: 3

✅ firebase-app-hosting-basics

• Status: Passed
• Findings: 2

✅ firebase-auth-basics

• Status: Passed
• Findings: 1

✅ firebase-hosting-basics

• Status: Passed
• Findings: 1

✅ firebase-security-rules-auditor

• Status: Passed
• Findings: 1
• Allowed (not blocking): 1
  • MANIFEST_MISSING_LICENSE (Allowed: firebase/agent-skills is licensed Apache-2.0 at the repository root; upstream does not embed an SPDX license identifier in per-skill SKILL.md frontmatter.)

---

Summary: Completed 5 of 5 skill scan(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]

Security triage complete.

Allowed findings: none. The official Firebase publisher and pinned source do not mitigate the following real risks:

• firebase-basics — LLM_COMMAND_INJECTION: user-controlled values are interpolated into shell templates, including a double-quoted display name; LLM_SUPPLY_CHAIN_ATTACK: npx -y firebase-tools@latest and remote skill/plugin updates execute mutable upstream artifacts.
• firebase-data-connect-basics — LLM_SUPPLY_CHAIN_ATTACK: mutable npx -y firebase-tools@latest is executed for initialization, generation, validation, and deployment; LLM_HARMFUL_CONTENT: the CRUD update/delete example authorizes any USER without a per-record ownership check.
• firebase-firestore — LLM_COMMAND_INJECTION: database IDs/locations are interpolated into shell commands without an argument-safe boundary.

No exclusion was added; these must remain blocking. Validated pinned sources with task validate-skill -- skills/firebase-basics, skills/firebase-data-connect-basics, and skills/firebase-firestore.

[danbarr]

Correction: deferred the firebase-basics, firebase-data-connect-basics, and firebase-firestore updates to their PR-base ref/version values. Final status depends on the authoritative GitHub Trusted Skill Scan.