codebase-integrity

Pass

Audited by Gen Agent Trust Hub on Jul 24, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing untrusted content from the codebase being audited.\n
  • Ingestion points: The instructions require the agent to read the project README, manifest files like package.json, and source code modules (SKILL.md).\n
  • Boundary markers: No specific boundary delimiters or instructions are provided to distinguish between the skill's directives and potentially malicious instructions within the audited files.\n
  • Capability inventory: The skill allows the agent to modify files via its 'AUTO-FIX RULES' and to execute shell commands like the project's type checker.\n
  • Sanitization: There is no requirement for the agent to sanitize or validate the content of the files it reads before acting on them.\n- [COMMAND_EXECUTION]: The skill instructs the agent to run the project's type checker. This involves shell command execution that could be exploited if project configuration files are maliciously crafted.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 24, 2026, 11:31 AM
Security Audit — agent-trust-hub — codebase-integrity