chronosforge-temporal-email-cli

Fail

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONPRIVILEGE_ESCALATION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions direct the agent to download a pre-built binary from a personal GitHub repository (randyfajar/inbox-watcher-cli).
  • [REMOTE_CODE_EXECUTION]: The installation guide and GitHub Actions examples encourage fetching a remote binary via wget and executing it after applying chmod +x. This pattern allows for the execution of arbitrary code from an unknown source.
  • [COMMAND_EXECUTION]: The provided Python, Node.js, and Bash examples demonstrate the use of subprocess.run, child_process.exec, and shell piping to execute the downloaded chronosforge binary with various arguments.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The skill is designed to monitor and extract data from external temporary email inboxes (SKILL.md).
  • Boundary markers: No explicit delimiters or boundary markers are defined to help the agent distinguish between instructions and untrusted email content.
  • Capability inventory: The skill possesses capabilities for shell execution, file system interaction via CLI, and network requests (curl).
  • Sanitization: There is no evidence of sanitization or filtering of the email content before it is parsed and used in automation workflows.
  • [PRIVILEGE_ESCALATION]: The integration examples for GitHub Actions include the use of sudo to move the downloaded binary into a protected system directory (/usr/local/bin/), which involves acquiring administrative permissions.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Oct 8, 2026, 11:44 PM