check-compiler-errors

Pass

Audited by Gen Agent Trust Hub on May 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill is designed to run arbitrary compilation and type-checking commands found within the user's repository. While this is the primary function of the skill, it relies on the safety of the local development environment.
  • [PROMPT_INJECTION]: There is a potential risk of indirect prompt injection. A malicious file in the repository could trigger a compiler error that contains instructions for the AI agent. If the agent processes these errors without sanitization, it might inadvertently follow embedded commands.
  • Ingestion points: Output from the repository's compile and type-check commands.
  • Boundary markers: None identified in the workflow to separate command output from agent instructions.
  • Capability inventory: The skill has the capability to run shell commands and apply fixes (file system writes).
  • Sanitization: No explicit sanitization or validation of the compiler output is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
May 26, 2026, 08:52 AM
Security Audit — agent-trust-hub — check-compiler-errors