ShareX Architecture and Porting
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [DATA_EXFILTRATION]: The skill references a hardcoded absolute file path
C:\Users\liveu\source\repos\ShareX Team\ShareX. While this exposes information about the host environment's directory structure and local username ('liveu'), it appears to be a legitimate reference to the source code repository for the project being ported. - [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process and port external source code, which could potentially contain embedded instructions.
- Ingestion points: Local file system content from the ShareX repository (SKILL.md).
- Boundary markers: There are no explicit delimiters or safety instructions provided to the agent to distinguish between its operational rules and the content of the files being analyzed.
- Capability inventory: The skill utilizes file system read/write operations and shell command execution (git).
- Sanitization: No sanitization or content validation steps are defined for the files processed during the porting task.
- [COMMAND_EXECUTION]: The guidelines instruct the agent to execute shell commands, specifically
git show, to retrieve historical versions of files and redirect them into a localrefdirectory for parity analysis.
Audit Metadata