skills/convex-dev/convex/etch/Gen Agent Trust Hub

etch

Pass

Audited by Gen Agent Trust Hub on Jul 26, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute the convex.jar utility via Bash to perform store operations such as integrity validation, garbage collection, and data migration.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions include reading data from external database files, which presents a surface for indirect prompt injection if the processed data contains malicious instructions.
  • Ingestion points: Data retrieved via etch read and etch dump subcommands in SKILL.md.
  • Boundary markers: None provided to distinguish between tool output and instructions.
  • Capability inventory: Shell command execution via Bash and file system access.
  • Sanitization: No explicit sanitization or filtering of database content is defined.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 26, 2026, 02:23 PM
Security Audit — agent-trust-hub — etch