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@latestto 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/andscripts/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