stack-detect

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes a local script scripts/detect-stack.mjs via the Bash tool to perform project analysis. The target directory is passed as an argument, which is a standard pattern for project-based agent tools.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing untrusted project data.
  • Ingestion points: Project files scanned via scripts/detect-stack.mjs (e.g., schema.prisma, models.py, structure.sql).
  • Boundary markers: No explicit delimiters or instructions are used to ignore embedded malicious prompts within the scanned files.
  • Capability inventory: The skill utilizes Bash, Read, and Glob tools.
  • Sanitization: No explicit sanitization or validation of the ingested file content is mentioned prior to processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 10:02 PM
Security Audit — agent-trust-hub — stack-detect