Skills
Navigate
skills/agoodway/goodskills/listex/Gen Agent Trust Hub

listex

Fail

Audited by Gen Agent Trust Hub on Oct 17, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill's documentation in README.md and SKILL.md includes instructions to install the listex CLI by downloading a script from the project's GitHub repository and piping it to a shell. This is presented as the primary method for binary resolution.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the Listex platform, such as news articles, job listings, and user-submitted tips, which could contain malicious instructions designed to influence the agent's behavior.
  • Ingestion points: Data is ingested via subcommands like listex news list, listex jobs match, and listex tips show.
  • Boundary markers: No explicit instructions are provided to use delimiters or ignore embedded commands within the ingested content.
  • Capability inventory: The agent has the capability to execute the listex CLI, which can perform network operations (API calls), create/delete content, and send real emails.
  • Sanitization: The instructions do not mention sanitization or validation of the text content retrieved from the platform.
Recommendations
  • HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/agoodway/listex/main/cli-rust/install.sh - DO NOT USE without thorough review
Audit Metadata
Risk Level
HIGH
Analyzed
Oct 17, 2026, 10:51 AM