threadline-gateway

Pass

Audited by Gen Agent Trust Hub on Jul 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the threadline CLI tool as its primary integration surface for all operations, including checking status, listing initiatives, and resolving decisions.
  • [INDIRECT_PROMPT_INJECTION]: The skill represents an attack surface for indirect prompt injection as it ingests untrusted data from an external Gateway.
  • Ingestion points: The agent reads data via threadline --json inbox list, threadline --json initiative list, and threadline --json decision get (found in references/cli.md).
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the fetched data are provided in the skill instructions.
  • Capability inventory: The agent has the capability to execute shell commands (via the threadline CLI) and perform further state mutations based on the fetched data (SKILL.md).
  • Sanitization: The instructions do not specify any validation or sanitization steps for the data retrieved from the remote Gateway.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 19, 2026, 08:26 AM
Security Audit — agent-trust-hub — threadline-gateway