create-user-story
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted text from third-party platforms which introduces an indirect prompt injection attack surface. * Ingestion points: Untrusted data is retrieved from external issue trackers (Linear, GitHub, Jira) during duplicate searches in Phase 2, along with user-supplied free-form text. * Boundary markers: Absent. No explicit delimiters or guardrail instructions are provided to prevent the agent from executing commands found within searched issue content. * Capability inventory: The skill possesses file write privileges (
04-projects/[project]/stories/), CLI execution capabilities (ghandjira), and network capabilities via WebFetch and Linear MCP. * Sanitization: Absent. External tracker content is evaluated directly without sanitization or structural validation.
Audit Metadata