Undeclared Tool Scope
- Category
- MCP Least Privilege
- Confidence
- 70% confidence
- Finding
Without declared permissions the skill's intent is opaque and cannot be validated.
- Content
Security audit
Security checks for vulnerabilities and agentic risk
This is a coherent Jira administration skill with expected Jira-changing examples, but users should review automation rules before applying them in production.
Install only if you want an agent to help with Jira administration. Before using its automation examples in a real Jira site, review destructive actions, auto-approval rules, outbound notifications, and webhooks with your Jira admins and data-governance requirements.
Without declared permissions the skill's intent is opaque and cannot be validated.
The file presents 'Delete issue' as a supported action and elsewhere describes recipes as production-ready, but it does not specifically warn that deletion is destructive and may be irreversible. The general best-practice note that mistakes can be destructive is helpful but does not clearly disclose the risk at the point where deletion is introduced.
The documentation explicitly promotes outbound actions like email, Slack, Teams, and web requests without a nearby warning that Jira smart values can contain sensitive issue data such as descriptions, emails, account IDs, and internal project metadata. In a Jira administration skill, users may copy these examples into production automation, causing unreviewed data disclosure to external systems or unintended recipients.
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
- Assign to product owner
- Send email notification
### Auto-approve small bugs
**Trigger:** Issue created
**Conditions:**
- Issue type = Bug
The rule automatically transitions low-priority bugs to Approved without human review. While not malicious, this is a genuine governance risk: automated approval can bypass required triage or change-control checks, and an attacker or careless user could intentionally understate severity to push issues through an approval gate.
- Priority IN (Low, Lowest)
**Actions:**
- Transition to "Approved"
- Add comment: "Auto-approved (low-priority bug)"
### Require security review
**Trigger:** Issue transitioned
The webhook example transmits issue summary, description, and assignee data to an external GitHub API, but the documentation provides no warning about data classification, consent, redaction, or trust boundaries. In a Jira automation skill, users may copy this pattern directly into production and unintentionally exfiltrate sensitive internal ticket content or personal data to a third-party system.