soia-dev-terminal-ops
Pass
Audited by Gen Agent Trust Hub on Jul 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill executes arbitrary shell commands, including tmux session management and a user-defined
FALLBACK_COMMAND. It mitigates associated risks by requiring explicit user confirmation before high-impact actions and advising against unsafe shell string concatenation. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface by reading external data that could be attacker-controlled.
- Ingestion points: The skill reads process logs via
tailand captures tmux pane content usingtmux capture-pane, which is then processed by the agent. - Boundary markers: No explicit delimiters or warnings are defined to isolate untrusted log content from agent instructions.
- Capability inventory: The skill can terminate processes (
kill -9) and execute arbitrary shell commands (FALLBACK_COMMAND). - Sanitization: The instructions recommend using host tool safe parameter passing rather than direct concatenation, but do not provide specific sanitization for data read from files.
- [EXTERNAL_DOWNLOADS]: The documentation references an installation command using
npxto fetch a package from thesoia-teamrepository, which corresponds to the skill's author.
Audit Metadata