hook-development
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The
scripts/test-hook.shutility facilitates local execution of hook scripts in a shell environment for testing purposes. - [DATA_EXFILTRATION]: Documentation in
references/advanced.mdprovides examples of sending notifications to external systems like Slack usingcurl, which represents a network capability for integration. - [PROMPT_INJECTION]: The skill manages the ingestion of untrusted data (Category 8) from user prompts and tool inputs across various hook events defined in
SKILL.md. It provides comprehensive mitigation through boundary enforcement, validation scripts (e.g.,examples/validate-write.sh), and sanitization guidance inreferences/migration.md.
Audit Metadata