capture-tasks-from-meeting-notes
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were identified. The skill implements a robust human-in-the-loop confirmation process (Step 5) which prevents the agent from creating Jira issues without explicit user approval.- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from Confluence pages or pasted text. While meeting notes could contain malicious instructions, the risk is minimized by the skill's reliance on specific regex-based extraction patterns (defined in references/action-item-patterns.md) and the requirement for the user to review and modify all parsed tasks before they are submitted to Jira via 'createJiraIssue'.- [DATA_EXPOSURE]: The skill accesses internal Atlassian resources (Confluence pages and Jira account IDs) using official API tools ('getConfluencePage', 'lookupJiraAccountId'). These operations are conducted within the authenticated context of the user and do not exfiltrate data to external domains.
Audit Metadata