lovable-testing

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from test plans, profiles, and results within the .lovable-agent/ directory, which serves as a potential vector for indirect instructions.
  • Ingestion points: Files located in .lovable-agent/tests/plans/, .lovable-agent/tests/profiles/, and .lovable-agent/tests/results/ are read into the agent context.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when handling these files.
  • Capability inventory: The skill allows for the execution of a migration script (scripts/migrate-workspace.py) and modification of project configurations.
  • Sanitization: No sanitization or validation logic is defined for the content of the processed test artifacts.
  • [COMMAND_EXECUTION]: The skill requires the agent to execute a Python script (scripts/migrate-workspace.py) to perform workspace migration, involving local shell execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 11:47 AM
Security Audit — agent-trust-hub — lovable-testing