setup-nest-profiler

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the project's detected package manager (npm, pnpm, or yarn) to install the core profiler and its collector modules as specified in SKILL.md and references/enable-strategies.md. This is the primary function for setting up the developer tools.
  • [EXTERNAL_DOWNLOADS]: The skill downloads packages from the official NPM registry, including vendor-owned libraries under the @eleven-labs scope and well-known dependencies such as nestjs-cls and @nestjs/config. These are standard resources for the target environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it ingests and processes content from the consumer's project files during its introspection phase.
  • Ingestion points: Files including package.json, main.ts, app.module.ts, nest-cli.json, and lockfiles are read in SKILL.md to determine the application stack.
  • Boundary markers: The skill does not explicitly define delimiters to separate ingested file content from its own instructions.
  • Capability inventory: The skill has the capability to execute shell commands for package installation and perform file system writes to create new modules and entrypoints.
  • Sanitization: There is no mention of sanitization or strict schema validation for the ingested project data before it is used to drive the installation logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 06:21 AM
Security Audit — agent-trust-hub — setup-nest-profiler