xit
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
xitCLI commands on the local system to manage version control tasks such as staging changes, committing, and branch management. - [EXTERNAL_DOWNLOADS]: The skill performs network operations via
xit clone,xit fetch, andxit pushto interact with remote repositories and update local data. - [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it reads and displays content from version control repositories, including commit logs, messages, and file diffs.
- Ingestion points: Untrusted data enters the agent context through the outputs of
xit status --cli,xit log --cli, andxit diff --clias specified inSKILL.md. - Boundary markers: Absent; the skill does not utilize delimiters or explicit instructions to ignore commands embedded in the repository content.
- Capability inventory: The skill allows the agent to modify the filesystem (
xit add,xit rm,xit restore) and perform network synchronization (xit push,xit fetch). - Sanitization: Absent; repository content is processed as raw text without validation, escaping, or filtering for malicious instructions.
Audit Metadata