chore(deps): update atlassian/forge-skills digest to 294b53d

[renovate]

This PR contains the following updates:

Package	Update	Change
atlassian/forge-skills	digest	a8eb109 → 294b53d

---

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

❌ forge-app-builder

• Status: Failed
• Findings: 4
• Blocking: 2

Blocking issues:

• [LLM_UNAUTHORIZED_TOOL_USE] (HIGH) The skill's stated invariants and creation guidance require explicit authorization immediately before accepting Forge terms or billing consent. However, the creation helper unconditionally appends --accept-terms whenever a developer-space ID is supplied. The helper has no parameter or interactive confirmation that represents explicit authorization, so use of the helper can accept external terms on the user's behalf. (scripts/create_forge_app.py)
• [LLM_COMMAND_INJECTION] (CRITICAL) The deployment helper constructs shell command strings from user-controlled command-line arguments and executes them with shell=True. Values such as --env, --site, --product, and --developer-space-id can contain shell metacharacters, allowing arbitrary commands to execute with the privileges of the agent or user running the helper. (scripts/deploy_forge_app.py)

✅ forge-app-review

• Status: Passed
• Findings: 0

❌ forge-debugger

• Status: Failed
• Findings: 12
• Blocking: 2

Blocking issues:

• [LLM_COMMAND_INJECTION] (HIGH) Several command templates interpolate values that may originate in user messages, such as an Atlassian site URL and error text. The templates do not require strict validation or shell-safe argument handling. If an agent passes these strings into a shell command as shown, shell metacharacters could turn a Forge command into arbitrary command execution. (SKILL.md)
• [LLM_UNAUTHORIZED_TOOL_USE] (HIGH) The instructions assert blanket authorization to run all diagnostics and fixes without asking permission, including global package installation, dependency installation, builds, deployments, and app installation/upgrades. These actions can modify the local development environment and remotely alter Forge application state. A skill must not override normal confirmation and authorization boundaries for consequential tool use. (SKILL.md)

---

Summary: Scanned 3 skill(s), found 4 blocking issue(s).

⚠️ Action Required: Review the blocking findings. Add a justified entry to the skill's security.allowed_issues[] in its spec.yaml if the finding is a false positive.

[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.