aiwg-refresh
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the
aiwgCLI and system utilities (ls,wc) to manage the project state and verify deployments. - [EXTERNAL_DOWNLOADS]: The
aiwg -updatecommand and the suggested manual installation method (curl | bash) involve downloading remote assets to the local system. - [REMOTE_CODE_EXECUTION]: The skill facilitates the installation of new 'agents' and 'commands' which are executable components within the AIWG framework.
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface.
- Ingestion points: The agent ingests and acts upon the output generated by the
aiwg -statusandaiwg -updatecommands. - Boundary markers: There are no explicit delimiters or instructions provided to distinguish between CLI output and subsequent agent instructions.
- Capability inventory: The agent has the capability to execute the
aiwgbinary, list files, and count lines via the shell. - Sanitization: No sanitization or validation of the CLI output is performed before it is processed by the agent.
Audit Metadata