enhance-cross-file
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local Node.js script located at
./lib/enhance/cross-file-analyzer.jsusing thenode -ecommand. This script performs the primary task of analyzing cross-file consistency. - [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves parsing and analyzing other files such as agents, skills, and workflows. This creates a surface for indirect prompt injection if those files contain malicious instructions, though the risk is minimized by the skill's implementation of structured JSON and markdown reporting.
- Ingestion points: Local project files and directories specified via arguments.
- Boundary markers: No explicit markers are defined for delimiting the content of analyzed files.
- Capability inventory: Execution of a specific local script and filesystem read access across the target project.
- Sanitization: No explicit content sanitization or instruction filtering is documented for the files being analyzed.
Audit Metadata