thread-management

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to interact with the 'alma' CLI for core operations like listing, creating, and deleting chat threads. This is the primary functionality of the skill.
  • [PROMPT_INJECTION]: The skill exposes an indirect prompt injection surface by retrieving and searching through chat thread messages.
  • Ingestion points: Message data is ingested via the 'alma thread messages' command and the local search API endpoint 'http://localhost:23001/api/threads/search'.
  • Boundary markers: There are no defined delimiters or 'ignore' instructions to prevent the LLM from potentially following instructions found within the retrieved thread messages.
  • Capability inventory: The agent has access to the 'Bash' tool, providing it with the ability to execute shell commands based on processed content.
  • Sanitization: The skill does not implement any visible sanitization or validation of the message content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 09:32 AM