cawplan-ticket-context
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests ticket data from an external system, creating a surface for indirect prompt injection if those fields contain malicious instructions.
- Ingestion points: Ticket 'description' and 'remarks' fields returned by the 'cawplan tickets search' command.
- Boundary markers: Absent; the skill does not instruct the agent to use specific delimiters or ignore instructions within the ticket content.
- Capability inventory: The skill uses the Bash tool to execute vendor-specific 'cawplan' commands.
- Sanitization: Absent; the skill directs the agent to display the raw content, including HTML fields, without filtering. These risks are mitigated by explicit instructions for the agent to stop after displaying the context.
Audit Metadata