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.sh to 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 in bmad-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, and Bash tools as defined in SKILL.md to 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
Risk Level
SAFE
Analyzed
Jun 20, 2026, 12:30 PM
Security Audit — agent-trust-hub — bmad-correct-course