dead-code-sweep

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: During the cleanup phase, the skill executes project-specific shell commands such as lint, typecheck, and build to verify that removing code did not break the application.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it ingests and interprets untrusted content from the user's codebase to drive its detection logic.
  • Ingestion points: The skill reads all source files, configuration files, and dependency manifests across the analyzed project.
  • Boundary markers: The instructions do not specify any delimiters or warnings to ignore potential instructions embedded within the analyzed code or comments.
  • Capability inventory: The skill possesses the ability to read, write, and delete files, as well as execute arbitrary shell commands through the project's build and linting system.
  • Sanitization: No sanitization or validation of the external codebase content is performed before it is processed by the agent's logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 07:19 PM