ecosystem-integrity-scanner
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The
scripts/main.cjsfile utilizeschild_process.execSyncto run a local Node.js script located at a specific path (scripts/validation/validate-ecosystem-integrity.cjs). The execution is performed withshell: false, which prevents shell-related injection vulnerabilities by bypassing the command shell and executing the process directly. - [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (Category 8) because it is designed to read and analyze various files within the framework, including agent frontmatter and source code.
- Ingestion points: Data enters the agent context through the outputs of
Glob,Grep, and the validation script which parse project files. - Boundary markers: Findings are organized into a structured markdown report as defined in
SKILL.md, although no specific adversarial-resistant delimiters are used for raw file content. - Capability inventory: The skill utilizes the
Bash,Read,Glob, andGreptools, and the associated script has the ability to execute local Node.js files. - Sanitization: The
scripts/main.cjsfile implements a strict regex whitelist that only extracts lines matching specific error tags (e.g.,[PHANTOM_REQUIRE],[PHANTOM_SKILL]), which prevents arbitrary text from being interpreted as instructions by the agent.
Audit Metadata