thread-management

Fail

Audited by Gen Agent Trust Hub on Feb 15, 2026

Risk Level: HIGHPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • Prompt Injection (HIGH): Vulnerable to Indirect Prompt Injection. 1. Ingestion points: The skill fetches untrusted data via alma threads (titles) and alma thread messages (message history). 2. Boundary markers: No delimiters or instructions are used to isolate this external content from the agent's system prompt. 3. Capability inventory: The agent has the powerful Bash tool and destructive commands like alma thread delete. 4. Sanitization: There is no evidence of filtering or sanitization of the retrieved content.
  • Command Execution (LOW): The skill utilizes the Bash tool for CLI interactions; while necessary for its intended functionality, this provides the mechanism for potential exploitation via prompt injection.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 15, 2026, 06:53 AM