chore(deps): update datadog-labs/agent-skills digest to 7f8b08f

[renovate]

This PR contains the following updates:

Package	Update	Change
datadog-labs/agent-skills	digest	bcbdc2b → 7f8b08f

---

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

✅ agent-observability-eval-bootstrap

• Status: Passed
• Findings: 1

✅ agent-observability-experiment-analyzer

• Status: Passed
• Findings: 4

✅ agent-observability-session-classify

• Status: Passed
• Findings: 1

✅ dd-apm

• Status: Passed
• Findings: 6
• Allowed (not blocking): 3
  • COMPOUND_EXTRACT_EXECUTE (Allowed: FP: cisco-ai-skill-scanner matched the documented pup CLI install
    snippet in k8s-ssi/agent-install/SKILL.md:67,
    k8s-ssi/troubleshoot-ssi/SKILL.md:48 and
    linux-ssi/troubleshoot-ssi/SKILL.md:48. The snippet downloads the
    official pup release tarball from the same vendor
    (github.com/datadog-labs/pup/releases, version pinned via the GitHub
    releases API) and pipes it through tar xz into /usr/local/bin — the
    canonical, vendor-published CLI install instruction shown to the user,
    not a hidden/malicious archive payload. No executable threat.
    datadog-labs/agent-skills @9bcb3ceafacae78dbba76c9459a878fc7d6a0d10.
    )
  • COMPOUND_EXTRACT_EXECUTE (Allowed: FP: cisco-ai-skill-scanner matched the documented pup CLI install
    snippet in k8s-ssi/agent-install/SKILL.md:67,
    k8s-ssi/troubleshoot-ssi/SKILL.md:48 and
    linux-ssi/troubleshoot-ssi/SKILL.md:48. The snippet downloads the
    official pup release tarball from the same vendor
    (github.com/datadog-labs/pup/releases, version pinned via the GitHub
    releases API) and pipes it through tar xz into /usr/local/bin — the
    canonical, vendor-published CLI install instruction shown to the user,
    not a hidden/malicious archive payload. No executable threat.
    datadog-labs/agent-skills @9bcb3ceafacae78dbba76c9459a878fc7d6a0d10.
    )
  • COMPOUND_EXTRACT_EXECUTE (Allowed: FP: cisco-ai-skill-scanner matched the documented pup CLI install
    snippet in k8s-ssi/agent-install/SKILL.md:67,
    k8s-ssi/troubleshoot-ssi/SKILL.md:48 and
    linux-ssi/troubleshoot-ssi/SKILL.md:48. The snippet downloads the
    official pup release tarball from the same vendor
    (github.com/datadog-labs/pup/releases, version pinned via the GitHub
    releases API) and pipes it through tar xz into /usr/local/bin — the
    canonical, vendor-published CLI install instruction shown to the user,
    not a hidden/malicious archive payload. No executable threat.
    datadog-labs/agent-skills @9bcb3ceafacae78dbba76c9459a878fc7d6a0d10.
    )

✅ dd-docs

• Status: Passed
• Findings: 3
• Allowed (not blocking): 1
  • MANIFEST_MISSING_LICENSE (Allowed: datadog-labs/agent-skills is licensed MIT at the repository root; upstream does not embed an SPDX license identifier in per-skill SKILL.md frontmatter.)

✅ dd-logs

• Status: Passed
• Findings: 1

✅ dd-monitors

• Status: Passed
• Findings: 3
• Allowed (not blocking): 1
  • ATR_2026_00066 (Allowed: FP: matched the Datadog monitor-message template placeholder {{host.name}} (SKILL.md:119). It is alert context substituted at delivery time, not an agent instruction or payload. datadog-labs/agent-skills @7f8b08f4fa57211ac1b2b42d9771c9e0c4d79124.)

✅ dd-pup

• Status: Passed
• Findings: 14
• Allowed (not blocking): 1
  • ATR_2026_00002 (Allowed: FP: matched the Markdown link text [setup instructions] in SKILL.md:42, which points to the upstream pup installation documentation; it is ordinary documentation, not an instruction-injection pattern. datadog-labs/agent-skills @7f8b08f4fa57211ac1b2b42d9771c9e0c4d79124.)

---

Summary: Completed 8 of 8 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:

• Allowed ATR_2026_00066 for dd-monitors: it matches the documented {{host.name}} monitor-message alert-context placeholder (SKILL.md:119), not an instruction or payload.
• Left LLM_COMMAND_INJECTION blocking for agent-observability-trace-rca: evals/executor.py interpolates caller-controlled fields into the /agent-observability-trace-rca prompt passed to invoke_skill() without validation or a typed channel. Publisher trust does not mitigate this injection path.

Validated with task validate-skill -- skills/dd-monitors.

[danbarr]

Follow-up: I trialed deferring only agent-observability-trace-rca. The remaining Datadog updates still scan with blocking findings in agent-observability-experiment-analyzer, dd-monitors, and dd-pup, so I did not push the partial revert or add further exclusions.

[danbarr]

Correction: deferred the agent-observability-trace-rca ref/version update to its PR-base values. The dd-monitors exclusion remains. Final status depends on the authoritative GitHub Trusted Skill Scan.