drumjangler-project-bmad

Warn

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: MEDIUMREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill uses npx --yes bmad-method@latest to fetch and execute a remote package from the NPM registry at runtime. This dependency is used to manage the 'BMad Method' installation status and modules.
  • [COMMAND_EXECUTION]: The skill requires the execution of multiple local shell scripts located in scripts/session-hooks/ and scripts/agent/ for session lifecycle and issue management tasks.
  • [INDIRECT_PROMPT_INJECTION]: The skill passes external issue identifiers (<ISSUE_ID>) as command-line arguments to shell scripts, creating a potential vector for command injection.
  • Ingestion points: Issue identifiers are sourced from Linear ticket names or user-provided input.
  • Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands in the input arguments.
  • Capability inventory: The skill has access to shell execution and network resources via npx.
  • Sanitization: The skill instructions do not include validation or escaping steps for the issue identifier before it is passed to shell scripts.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 4, 2026, 06:55 AM
Security Audit — agent-trust-hub — drumjangler-project-bmad