jira-integration
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references the installation of the
mcp-atlassianpackage (version 0.21.0) using theuvxtool. This is a standard and verifiable dependency for Atlassian MCP services. - [COMMAND_EXECUTION]: The skill documents the use of
curlanduvxfor interacting with Jira's API and running the MCP server. These commands are standard for the described functionality and operate within the user's configured environment. - [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection due to its core function of ingesting and analyzing Jira ticket content.
- Ingestion points: Reads ticket summaries, descriptions, and comments from the Jira REST API via
SKILL.mdexamples. - Boundary markers: No specific delimiters or instructions to ignore embedded commands are used in the provided templates.
- Capability inventory: Uses
curlfor network requests anduvxfor subprocess execution. - Sanitization: There is no evidence of sanitization or filtering of external data before processing.
Audit Metadata