jira
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local shell commands using the
jiraCLI and invokes Atlassian Model Context Protocol (MCP) tools to perform issue management tasks. - [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
jira-clifrom a third-party GitHub repository and provides a command to install a helper skill from the author's own GitHub repository (bondansebastian/agent-skills) usingnpx. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes untrusted data from Jira issue fields (summaries, descriptions, and comments) which could contain malicious instructions.
- Ingestion points: Data is retrieved via
mcp__atlassian__getJiraIssueandjira issue view(SKILL.md, references/mcp.md). - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands when processing ticket content.
- Capability inventory: The agent can create pull requests, make commits, and modify Jira issues based on the processed data.
- Sanitization: No explicit sanitization or validation of the ingested Jira content is performed before use in prompts.
Audit Metadata