architect
Warn
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONDYNAMIC_EXECUTIONPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTIONOBFUSCATION
Full Analysis
- [COMMAND_EXECUTION]: The
check-runner.ps1andcheck-runner.shscripts are designed to parse markdown documentation for commands (prefixed with- RUN:) and execute them directly usingInvoke-Expression(PowerShell) orbash -c(Bash). - [DYNAMIC_EXECUTION]: The
check-runner.ps1script dynamically generates a PowerShell wrapper for each check command at runtime, which is then executed as a sub-process. - [PRIVILEGE_ESCALATION]: The
dispatch.mdfile contains explicit instructions for the agent to use the--sandbox danger-full-accessflag when launching builder and strategist jobs. This intentionally opts out of default security constraints to bypass technical issues with restricted environments. - [INDIRECT_PROMPT_INJECTION]: The skill creates a vulnerability surface for indirect prompt injection through its core orchestration loop. 1. Ingestion points: The skill ingests untrusted data from GitHub issue comments and local job reports in
docs/jobs/. 2. Boundary markers: While some dispatch templates use separators, the raw ingestion from trackers lacks robust boundary enforcement. 3. Capability inventory: The skill possesses high-impact capabilities including arbitrary command execution (check-runner), git operations (postflight), and process spawning (run-job). 4. Sanitization: There is no evidence of explicit input sanitization or validation of external content before it is processed by the agent. - [OBFUSCATION]: The
check-runner.ps1script utilizes Base64 encoding to wrap and pass commands to PowerShell's-EncodedCommandparameter, which can obscure the intent of the executed code from static analysis tools.
Audit Metadata