paper-spine-ui
Warn
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The configuration wizard
scripts/intake_wizard.pyusesos.systemto executechcpfor character set configuration andclsorclearto manage the terminal display. - [COMMAND_EXECUTION]: The PowerShell launcher
scripts/launch_paperspine_ui.ps1usesStart-Processto spawn a new PowerShell instance to run the wizard. - [COMMAND_EXECUTION]: The Bash launcher
scripts/launch_paperspine_ui.shusesosascript(macOS) and various terminal emulators likegnome-terminal,konsole, andxterm(Linux) to execute shell commands in a new window. - [PRIVILEGE_ESCALATION]: The instructions in
SKILL.mddirect the agent to requestsandbox_permissions: require_escalatedto ensure the UI window appears reliably in sandboxed environments. - [PRIVILEGE_ESCALATION]: The PowerShell wrapper
scripts/launch_paperspine_ui.ps1and instructions inSKILL.mdutilize the-ExecutionPolicy Bypassflag to execute local scripts, bypassing default Windows script execution restrictions. - [DYNAMIC_EXECUTION]: The Bash launcher
scripts/launch_paperspine_ui.shdynamically constructs command strings that are executed in new process contexts via terminal utilities orosascript. - [INDIRECT_PROMPT_INJECTION]: The script
scripts/intake_wizard.pyautomatically reads Markdown and text files from the user's workspace to infer configuration values like 'motivation' and 'official URLs'. This ingestion of untrusted data represents an attack surface for indirect prompt injection. - Ingestion points:
scripts/intake_wizard.pyreads*.mdand*.txtfiles viaread_small_text_files;scripts/humanize_check.pyreads all*.texfiles in thefinal_paperdirectory. - Boundary markers: None; raw file contents are processed without delimiters or instructions to ignore embedded commands.
- Capability inventory: The skill can write configuration and report files (
paper_spine_config.json,paper_spine_config.md,humanize_report.md) and execute shell commands via its TUI wrappers. - Sanitization: No sanitization or validation of the ingested content is performed before it is processed for inference or presented to the user.
Audit Metadata