rlm-test-suite
Pass
Audited by Gen Agent Trust Hub on Jul 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill documents the execution of local test commands using
makeanduv run pytest. This is intended for standard development and validation workflows within the repository. - [PROMPT_INJECTION]: The
fleet-rlm daytona-smokecommand accepts a--repo <url>argument, which allows the skill to ingest and process content from external, potentially untrusted repositories. This constitutes an indirect prompt injection surface (Category 8). - Ingestion points: External repository content processed by the
daytona-smokecommand documented inSKILL.md. - Boundary markers: No specific boundary markers or instructions to ignore embedded content are provided in the skill instructions.
- Capability inventory: The skill uses
uv run pytestandmakewhich involve subprocess execution capabilities. - Sanitization: No sanitization or validation of the external repository content is documented.
Audit Metadata