scan-automation-project
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted project source code and can clone external repositories, creating an attack surface where malicious instructions embedded in those files could influence agent behavior.
- Ingestion points: Local source files, view templates, and external git repositories cloned into the
.testeiya/directory. - Boundary markers: The skill uses specific markdown comment tags (
<!-- test ... -->) to parse test cases but lacks explicit "ignore instructions" directives for the general content of scanned files. - Capability inventory: The skill can execute shell commands (
find,awk), vendor-specific tools vianpx(@testomatio/reporter,check-tests), and perform git operations (git clone). - Sanitization: No specific sanitization or validation of the ingested content is mentioned.
- [COMMAND_EXECUTION]: The skill utilizes shell commands such as
findandawkto parse test files and employs vendor-specific CLI tools throughnpxto perform its primary function of project analysis and reporting. - [EXTERNAL_DOWNLOADS]: The skill downloads vendor-specific packages (
@testomatio/reporter) and provides functionality to clone external git repositories based on user input during the setup process.
Audit Metadata