cawplan-ticket-context

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute cawplan CLI commands, including cawplan skill check and cawplan tickets search. These commands are used to interact with the vendor's infrastructure to retrieve ticket data.
  • [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes external content (titles, descriptions, and comments) from CawPlan tickets and injects this data directly into the agent's current conversation context.
  • Ingestion points: Data is ingested in SKILL.md through the cawplan tickets search command based on user-provided URLs or IDs.
  • Boundary markers: Absent. The instructions do not direct the agent to wrap the retrieved ticket content in delimiters or provide warnings to ignore embedded instructions.
  • Capability inventory: The skill is granted allowed-tools: Bash, which allows for shell command execution.
  • Sanitization: Absent. There is no evidence of content filtering, escaping, or validation of the text returned from the ticket system before it is presented in the context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 07:18 AM
Security Audit — agent-trust-hub — cawplan-ticket-context