Skills
skills/akillness/oh-my-skills/bmad-orchestrator/Gen Agent Trust Hub

bmad-orchestrator

Fail

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill uses a high-risk installation pattern in scripts/install.sh and SETUP.md that pipes a remote shell script from https://plannotator.ai/install.sh directly into sh. This allows for arbitrary code execution from an unvetted source.\n- [DATA_EXFILTRATION]: The scripts/phase-gate-review.sh script is designed to send the full text of project deliverables (such as PRDs and architecture specs) to the external service plannotator.ai via the plannotator submit command, potentially exposing sensitive project information.\n- [COMMAND_EXECUTION]: Several scripts, including scripts/check-status.sh and scripts/phase-gate-review.sh, use python3 -c to execute dynamically generated Python code for YAML parsing and process management.\n- [PROMPT_INJECTION]: The skill exhibits an Indirect Prompt Injection surface by reading and processing project documents (Ingestion points: docs/*.md) without sanitization or boundary markers. This creates a risk where malicious instructions embedded in documents could manipulate the agent's behavior during later implementation phases.
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
CRITICAL
Analyzed
Mar 11, 2026, 01:20 PM