Detects prompt-injection, jailbreak, and secret-leak patterns on the agent/pre-step, tools/pre-execute, and tools/post-execute seams with allow/ask/block tiers, sanitized defend/detection audit events, a defend_report tool, and a destructive-delete command guard.
- Version
- v0.2.0
- License
- Apache-2.0
- Added
- 2026-08-23
GitHub info
- License
- Apache-2.0
- Primary language
- TypeScript
- Last push
- Aug 21, 2026, 7:02 AM
- Maintainer
- PerryLink
- Added
- 2026-08-23
Install
dsh plugin --profile web add dsh-defendTags
README badge
Add this Markdown to your plugin README to link back to its listing.
[](https://dshget.com/plugins/PerryLink/dsh-defend)Related plugins
Security & Permissionsdsh-mask
PII masking for DeepSeek Harness — anonymizes names, phones, emails, ids, and keys before requests and restores them at the display layer, keeping plaintext out of session logs.
dsh-secure-audit
★ 65Read-only security and compliance plugin for DeepSeek Harness: prompt-injection detection, Chinese-PII redaction, and a local configuration audit with redacted, reproducible reports.
dsh-auto-review
★ 120Second-model auto-review on the approval answerer chain: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default.