sourcing-from-atlassian

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of external data from Jira issues and Confluence pages, creating an attack surface for indirect prompt injection if the source content contains malicious instructions.
  • Ingestion points: Data is retrieved from the Atlassian MCP server using tools such as getJiraIssue and getConfluencePage as detailed in SKILL.md.
  • Boundary markers: The skill instructions enforce a strict 'Source Bundle' output format (defined in Section 6) that uses Markdown headers and delimiters to isolate retrieved content from the agent's core instructions.
  • Capability inventory: No high-risk capabilities, such as arbitrary code execution, shell access, or unauthorized network operations, were identified in the skill instructions.
  • Sanitization: Section 3a specifies content cleaning procedures, including the removal of HTML tags and the conversion of Atlassian Document Format (ADF) into plain text or structured Markdown.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 08:13 AM