qlty-during-development
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
qltycommand-line tool, which is a recognized resource from the vendor 'parcadei', to perform code linting and formatting operations via the shell.\n- [INDIRECT_PROMPT_INJECTION]: The skill instructions involve the agent reading and processing local source code files, which constitutes an attack surface for indirect prompt injection.\n - Ingestion points: The skill operates on local source code files (e.g.,
src/sdk/providers.ts) that the agent is instructed to check or format.\n - Boundary markers: The instructions lack explicit boundary markers or warnings for the agent to disregard instructions that might be embedded within the source code files.\n
- Capability inventory: The agent is empowered to run shell commands (
qlty check) and apply automatic fixes to files (--fix), combining read and write capabilities.\n - Sanitization: No sanitization or validation of the file content is described in the skill before the tools are invoked.
Audit Metadata