cursor-check-compiler-errors
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes and summarizes output from compilation and type-checking commands. If a malicious codebase includes crafted strings (e.g., in comments, variable names, or string literals) that the compiler then emits in an error message, these could influence the agent's summary or subsequent fixing actions.
- Ingestion points: SKILL.md (Workflow Step 2: Summarize errors).
- Boundary markers: Absent.
- Capability inventory: File-write (Workflow Step 3: Fix issues), Subprocess execution (Workflow Step 1: Run repo's compile and type-check commands).
- Sanitization: Absent.
- [COMMAND_EXECUTION]: The skill requires the agent to execute repository-defined compilation and type-checking commands. This is the intended primary purpose of the skill, but it involves executing commands which may be controlled by the repository configuration.
Audit Metadata