bg-jobs

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill's primary purpose is the execution of arbitrary shell commands in the background via the bg run command. This allows the agent to manage multiple concurrent tasks.
  • [EXTERNAL_DOWNLOADS]: The skill instructions recommend installing the agentcli-helpers package from a public registry using uv tool install to provide the underlying CLI functionality.
  • [DATA_EXPOSURE]: The skill stores job metadata, standard output, and standard error logs in a local directory (agentcli_bgjobs/) within the OS temporary folder. While these files are local, they contain the full output of any commands executed by the agent.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it reads and processes the output of background jobs (bg read, bg logs) which may contain untrusted data or instructions from external processes. No specific boundary markers or sanitization logic for this output are mentioned in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 10:59 AM
Security Audit — agent-trust-hub — bg-jobs