migration-guard

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes content from database migration files and project configuration files without utilizing boundary markers or explicit isolation instructions. This creates a surface for indirect prompt injection, where malicious instructions embedded in a migration file (e.g., within SQL comments) could attempt to override the agent's behavior.
  • Ingestion points: The skill (Step 2 and 3) reads files provided in $ARGUMENTS, files identified via git diff, and various framework configuration files such as go.mod, alembic.ini, and .sql files.
  • Boundary markers: Absent. The skill does not instruct the agent to use delimiters or treat the imported file content as data rather than instructions.
  • Capability inventory: The agent is granted access to Bash, Read, Grep, and Glob tools, which allow for broad file system access and shell execution.
  • Sanitization: No sanitization, escaping, or validation of the external file content is performed before it is analyzed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 06:18 PM
Security Audit — agent-trust-hub — migration-guard