skills/airclear/skills/bmad-sync/Gen Agent Trust Hub

bmad-sync

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands including rm -rf, mkdir -p, and cp -rv to synchronize local files between the references/ and skills/ directories.
  • [COMMAND_EXECUTION]: The instructions reference the use of a tool named skills-ref for validating the synchronized file structure.
  • [PROMPT_INJECTION]: The synchronization process creates an indirect prompt injection surface where untrusted data could be introduced into other skills. Ingestion points: The agent reads from the references/bmad-[version]/ directory. Boundary markers: The instructions lack explicit delimiters or 'ignore' directives for the synced content. Capability inventory: The skill uses rm, mkdir, and cp for filesystem operations. Sanitization: No content validation or sanitization is performed on the synchronized source files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 08:17 PM