parallel-execution
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local shell script at .opencode/skills/task-management/router.sh to determine task parallelization and status. This command is restricted to a specific internal path and is necessary for the skill's operation.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it consumes task data to drive sub-agent behavior. * Ingestion points: The agent reads task instructions from JSON files located in .tmp/tasks/. * Boundary markers: No specific delimiters are identified to isolate untrusted task content. * Capability inventory: The orchestration flow can invoke a CoderAgent for file-system modifications and execute a local router script. * Sanitization: No sanitization of task file content is defined in the instructions.
Audit Metadata