preen-file-limits

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it reads and processes project source code which could contain malicious instructions.
  • Ingestion points: Project source code files identified as exceeding size limits (referenced in SKILL.md).
  • Boundary markers: The skill lacks explicit delimiters or instructions to ignore embedded prompts within the source code being refactored.
  • Capability inventory: The skill can execute shell commands via pnpm and git, modify the file system, and push changes to a repository.
  • Sanitization: Validation relies on standard post-refactoring checks (lint, type-check, tests) rather than sanitization of the ingested content.
  • [COMMAND_EXECUTION]: The skill executes local scripts and standard development tools as part of its routine operation.
  • Evidence: Execution of ./scripts/checks/checkFileLimits.sh for file discovery and pnpm for validation of refactored components.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 10:13 PM