windsurf-incident-runbook
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes shell commands via
gitandcurlto perform incident response operations, such as identifying and reverting problematic commits and checking the official Windsurf status page. - Evidence: Commands include
git revert,git push, andcurl -sf https://status.windsurf.com. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests and processes external data from repository history and configuration files.
- Ingestion points: Git commit logs (
git log) and configuration files (.windsurfrules,.codeiumignore) are read into the agent's context. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the scripts.
- Capability inventory: The skill has the capability to execute shell commands (
git,curl) and perform file system operations (mkdir,cp). - Sanitization: The skill does not implement specific sanitization or validation of the content read from git logs or configuration files.
Audit Metadata