run-tests
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
docker execanddocker psto manage and run tests inside a containerized environment. It executes shell commands to switch users within the container (su $(id -un)) and runpytest. This is standard behavior for a development tool designed to automate testing. - [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and report test results, which constitutes an ingestion surface for potentially untrusted data if test logs are manipulated.
- Ingestion points: The output of the
pytestexecution inSKILL.mdis ingested by the agent to provide feedback on failures. - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded content in the test output.
- Capability inventory: The skill possesses command execution capabilities through the
Bashtool for Docker management. - Sanitization: No sanitization or filtering is performed on the test output before it is presented to the agent's context.
Audit Metadata