create-user-story
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill employs
gh(GitHub CLI) andjiraCLI tools for issue searching and creation. - [EXTERNAL_DOWNLOADS]: Data is retrieved from well-known services including GitHub, Linear, and Jira to perform duplicate checks.
- [DATA_EXFILTRATION]: Accesses local configuration files in the
00-inbox/directory, such asMY-PROFILE.mdandMY-INTEGRATIONS.md, to retrieve user and project context. - [PROMPT_INJECTION]: An indirect prompt injection surface is present as the skill ingests issue titles and descriptions from external project trackers.
- Ingestion points: Issue data from GitHub, Linear, and Jira APIs.
- Boundary markers: Absent; external content is presented to the user without specific isolation or instructions to ignore embedded commands.
- Capability inventory: Local file writing to the project vault and remote issue creation.
- Sanitization: No explicit sanitization or filtering is applied to the content retrieved from external trackers before it enters the agent context.
Audit Metadata