spec-to-backlog
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates entirely within the Atlassian ecosystem using verified tools for data retrieval and issue creation, matching its stated purpose and author identity.
- [PROMPT_INJECTION]: The skill ingests untrusted content from Confluence. 1. Ingestion point: getConfluencePage in SKILL.md. 2. Boundary markers: None. 3. Capability inventory: createJiraIssue in SKILL.md. 4. Sanitization: The user must explicitly confirm the backlog breakdown in Step 4 before creation proceeds.
- [DATA_EXFILTRATION]: No instances of sensitive data exposure or network calls to unauthorized external domains were detected.
Audit Metadata