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