jira-sprint-dashboard
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted text data from Jira issues, such as summaries and labels, which could potentially contain malicious instructions.
- Ingestion points: Data is retrieved from Jira API fields including key, summary, and custom fields (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the ingested Jira content.
- Capability inventory: The skill has the capability to write files, specifically .canvas.tsx and static HTML artifacts, based on the external data.
- Sanitization: There is no explicit requirement for the agent to sanitize or escape the Jira content before it is interpolated into the generated dashboard code.
- [DYNAMIC_EXECUTION]: The skill involves the dynamic generation of executable code for dashboard rendering in the Cursor environment.
- Evidence: The instructions require the creation of a .canvas.tsx file with Jira data embedded directly into the component code (SKILL.md).
- Environment access: The agent is instructed to read local SDK configuration files at ~/.cursor/skills-cursor/canvas/sdk/ to inform the code generation process.
Audit Metadata