skills/getsentry/sentry/setup-dev/Gen Agent Trust Hub

setup-dev

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPERSISTENCEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: Downloads and executes the official Homebrew installation script from raw.githubusercontent.com/Homebrew/install.
  • [REMOTE_CODE_EXECUTION]: Downloads and executes the devenv installation script from the author's official GitHub repository (getsentry/devenv).
  • [PERSISTENCE]: Modifies shell configuration files (~/.zshrc, ~/.bashrc) to persist changes to the system PATH and initialize the direnv hook.
  • [COMMAND_EXECUTION]: Executes various system and development tools, including xcode-select, brew, docker, and git, to configure the local machine environment.
  • [DYNAMIC_EXECUTION]: Provides Python code snippets and patching instructions for the agent to modify local scripts (devservices.py) at runtime to add support for different Docker runtimes.
  • [INDIRECT_PROMPT_INJECTION]: Vulnerability surface identified for processing external data.
  • Ingestion points: Reads local source code (devservices.py) and retrieves external documentation using the al_search_docs MCP tool.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are present when handling this external data.
  • Capability inventory: The skill has access to shell execution, file system modification, and network operations.
  • Sanitization: There is no evidence of sanitization or validation of the content ingested from the source code or documentation before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 07:56 PM
Security Audit — agent-trust-hub — setup-dev