cawplan-ticket-create
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted long-form text from external sources (PRDs, Slack threads, meeting transcripts) to identify and extract ticket data.\n
- Ingestion points: Workflow B in
SKILL.mdis dedicated to processing pasted external text context.\n - Boundary markers: No specific boundary markers or "ignore" instructions are present to differentiate between data and potentially malicious instructions within the source text.\n
- Capability inventory: The skill utilizes
cawplan tickets create-versionandcawplan tickets create-backlogto write to the CawPlan system.\n - Sanitization: Safety is maintained through a strict requirement for a "Preview before creating" step where the user must explicitly approve the extracted candidates before any CLI commands are executed.
Audit Metadata