Skills
skills/supercent-io/skills-template/bmad-orchestrator/Gen Agent Trust Hub

bmad-orchestrator

Fail

Audited by Gen Agent Trust Hub on Mar 16, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The scripts/install.sh script and SETUP.md documentation instruct the user or agent to download a script from https://plannotator.ai/install.sh and pipe it directly to the shell (sh). This pattern allows for unauthenticated code execution from a third-party remote source, which can lead to full system compromise.\n- [EXTERNAL_DOWNLOADS]: The skill setup process involves downloading executable installation scripts and CLI tools from the external domain plannotator.ai.\n- [COMMAND_EXECUTION]: The skill relies on multiple bash scripts (init-project.sh, check-status.sh, phase-gate-review.sh, install.sh) to perform its primary functions, including environment configuration, file system manipulation, and invocation of system tools like python3 and yq.\n- [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes untrusted documentation files created during the workflow.\n
  • Ingestion points: Document files such as docs/prd-*.md and docs/architecture-*.md read by scripts/phase-gate-review.sh.\n
  • Boundary markers: None present to delimit user-provided content from instructions.\n
  • Capability inventory: Subprocess execution of the plannotator CLI and transmission of document content over the network.\n
  • Sanitization: No sanitization or validation of document content is performed before the data is read and piped to external commands.
Recommendations
  • HIGH: Downloads and executes remote code from: https://plannotator.ai/install.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 16, 2026, 09:29 AM