autorekt

Pass

Audited by Gen Agent Trust Hub on Nov 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill documentation describes a --hook parameter for the autorekt watch command. This feature allows the user (or an agent following these instructions) to specify a shell command that will be executed by a background daemon whenever a specific market condition is met. While the skill advises obtaining user approval, this creates a mechanism for persistent, conditional command execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes live, third-party market data from various external sources (exchanges, news feeds, prediction markets). This data is ingested into the agent's context to answer questions.
  • Ingestion points: Market data, news headlines, and calendar events fetched via autorekt show and autorekt why (SKILL.md).
  • Boundary markers: The skill instructs the agent to quote values and timestamps but does not specify strict delimiters for the external text.
  • Capability inventory: The skill uses autorekt CLI which can perform network requests and, via the watch command, execute shell hooks.
  • Sanitization: No explicit sanitization of the fetched text/headlines is mentioned before the agent processes it.
  • [EXTERNAL_DOWNLOADS]: The skill requires a binary that is not included. It directs users to download and install the autorekt binary from GitHub (github.com/autorekt/autorekt) or autorekt.com. Following the trust-scope-rule, these are documented neutrally as they are the official sources for the tool described in the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 14, 2026, 04:34 PM