build-run-debug
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on executing shell commands and scripts to perform its core functions. It specifically targets a project-local script located at
script/build_and_run.shand uses system binaries such asxcodebuild,pgrep, and/usr/bin/opento manage application lifecycles. - [INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface by ingesting and processing data from external sources during its diagnostic phase.
- Ingestion points: The agent is instructed to read and classify failures from compiler output, linker errors, and unified system logs (SKILL.md).
- Boundary markers: There are no requirements for delimiters or protective markers to prevent instructions embedded within error logs from influencing agent behavior.
- Capability inventory: The skill has permissions to execute local scripts, build tools, and process management commands, and can initialize git repositories.
- Sanitization: The instructions lack any requirement for sanitizing or escaping the log data before it is interpreted by the agent.
Audit Metadata