bmad-correct-course
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local shell script located at
${CLAUDE_PLUGIN_ROOT}/scripts/scope-conflict-check.shto validate structural consistency of project stories. This execution is limited to a pre-defined plugin path. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes content from multiple external documentation files which may contain untrusted data.
- Ingestion points: The skill reads
bmad-output/prd.md,bmad-output/architecture.md, and all files inbmad-output/stories/to determine the project state. - Boundary markers: No explicit delimiters or instructions are used to distinguish user data from system instructions during processing.
- Capability inventory: The skill utilizes
Read,Write,Edit, andBashtools as defined inSKILL.mdto modify project files and run local validation scripts. - Sanitization: No explicit sanitization or filtering of the content within the ingested planning files is performed before the agent processes them.
Audit Metadata