start
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands (
grep,ls) to identify project-specific configurations, such as toolkit modules on the classpath and Makefile targets. These commands are used for environment discovery and are restricted to read-only operations on specific build and configuration files.- [INDIRECT_PROMPT_INJECTION]: The skill analyzes external project files to determine its execution flow, creating a surface for indirect prompt injection from untrusted project content. - Ingestion points: Reads project configuration files including
*.gradle.kts,*.toml, and theMakefile(referenced in SKILL.md). - Boundary markers: The skill does not define specific boundary markers or delimiters for the data read from these files.
- Capability inventory: Includes execution of shell commands for file searching and the conditional loading of additional modular instructions based on file content.
- Sanitization: No specific sanitization or validation of the file content is performed prior to processing.
Audit Metadata