triage
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from GitHub and Jira issue trackers, creating a surface for indirect prompt injection where malicious instructions in issue bodies or comments could influence agent behavior.
- Ingestion points: The skill reads issue bodies, comments, and PR diffs as defined in the 'Gather' step of
SKILL.mdand Step 1 ofREFERENCE.md. - Boundary markers: No specific delimiters or "ignore instructions" markers are used when interpolating external content into the agent's context.
- Capability inventory: The skill has the ability to comment on issues, apply/remove labels, and transition statuses using the
ghandacliCLIs (detailed intracker-github.mdandtracker-jira.md). - Sanitization: No sanitization or validation of the external content is performed before processing.
- [COMMAND_EXECUTION]: The skill invokes the GitHub CLI (
gh) and the Atlassian CLI (acli) to manage issue lifecycle tasks. These commands are documented as part of the intended triage functionality. - [EXTERNAL_DOWNLOADS]: The skill references the official Atlassian CLI tool (
acli) for Jira integration, providing a link to Atlassian's official developer documentation.
Audit Metadata