chore(deps): update getsentry/skills digest to c2f99a5

[renovate]

This PR contains the following updates:

Package	Update	Change
getsentry/skills	digest	6abccd6 → c2f99a5

---

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

✅ agents-md

• Status: Passed
• Findings: 2
• Allowed (not blocking): 1
  • MANIFEST_MISSING_LICENSE (Allowed: getsentry/skills is licensed Apache-2.0 at the repository root; upstream does not embed an SPDX license identifier in per-skill SKILL.md frontmatter.)

✅ code-review

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

✅ code-simplifier

• Status: Passed
• Findings: 1

✅ commit

• Status: Passed
• Findings: 0

✅ create-branch

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

✅ django-access-review

• Status: Passed
• Findings: 0

✅ django-perf-review

• Status: Passed
• Findings: 0

✅ doc-coauthoring

• Status: Passed
• Findings: 1

✅ find-bugs

• Status: Passed
• Findings: 4
• Allowed (not blocking): 3
  • ATR_2026_00051 (Allowed: False positive (excessive_autonomy) - matches ordinary quantifier words ('all files', 'All database', 'EVERY item', 'Unbounded operations', 'every file') inside a read-only security-review checklist enumerating what to inspect (attack surface mapping and a DoS checklist item literally named 'Unbounded operations'), not instructions granting the agent broad destructive authority.)
  • ATR_2026_00051 (Allowed: False positive (excessive_autonomy) - matches ordinary quantifier words ('all files', 'All database', 'EVERY item', 'Unbounded operations', 'every file') inside a read-only security-review checklist enumerating what to inspect (attack surface mapping and a DoS checklist item literally named 'Unbounded operations'), not instructions granting the agent broad destructive authority.)
  • ATR_2026_00051 (Allowed: False positive (excessive_autonomy) - matches ordinary quantifier words ('all files', 'All database', 'EVERY item', 'Unbounded operations', 'every file') inside a read-only security-review checklist enumerating what to inspect (attack surface mapping and a DoS checklist item literally named 'Unbounded operations'), not instructions granting the agent broad destructive authority.)

✅ gh-review-requests

• Status: Passed
• Findings: 0

✅ gha-security-review

• Status: Passed
• Findings: 0

✅ prompt-optimizer

• Status: Passed
• Findings: 0

✅ security-review

• Status: Passed
• Findings: 0

✅ skill-writer

• Status: Passed
• Findings: 1

---

Summary: Completed 14 of 14 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 for the four blocking findings at c2f99a5b04b4cd992ec3022d7c2c3e23e938d241:

• LLM_UNAUTHORIZED_TOOL_USE (claude-settings-audit): not allowlisted. The read-only baseline includes Bash(gh api:*) (SKILL.md:92), which can mutate arbitrary GitHub resources.
• LLM_PROMPT_INJECTION (iterate-pr): not allowlisted. It treats fetched PR comments as high/medium feedback to fix immediately (SKILL.md:52-66, 122-124) before commit/push, with no untrusted-content boundary.
• LLM_COMMAND_INJECTION (pr-writer): not allowlisted. The generated title is interpolated into shell commands (SKILL.md:117,124) using unsafe single-quote quoting.
• LLM_COMMAND_INJECTION (skill-scanner): not allowlisted. A user-provided directory is used directly in unquoted shell commands (SKILL.md:36,43-45,53).

getsentry/skills is a trusted publisher and the existing license/documentation exclusions remain unchanged, but publisher trust does not mitigate these exploitable workflows. No exclusions were added; all four findings correctly remain blocking.

[danbarr]

Follow-up: I trialed deferring the four initially flagged updates (claude-settings-audit, iterate-pr, pr-writer, and skill-scanner). The remaining set still has two critical ATR_2026_00030 findings in code-review, so I did not push the partial revert or add exclusions.

[danbarr]

Correction: deferred the claude-settings-audit, iterate-pr, pr-writer, and skill-scanner updates to their PR-base refs and versions. Final status depends on the authoritative GitHub Trusted Skill Scan.