pr-check
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local shell commands (
composer validate,vendor/bin/phpcs,vendor/bin/phpstan,vendor/bin/phpunit) to perform code validation and testing. This behavior is consistent with the skill's stated purpose of running a local CI suite. - [INDIRECT_PROMPT_INJECTION]: The skill processes output from external command-line tools which may contain content from the codebase being tested.
- Ingestion points: Standard output and error streams from the executed CI commands are fed back into the agent's context.
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential malicious content within command outputs.
- Capability inventory: The skill has the ability to execute shell commands sequentially based on the success of previous steps.
- Sanitization: There is no explicit sanitization or filtering of the command output before it is reported to the user or processed by the agent.
Audit Metadata