CharlotteN7/dsh-dlp

CharlotteN7★ 0TypeScript最后同步: 2026-08-16

在 GitHub 打开

Stops a DeepSeek Harness agent from reading your credential files and pasting secrets into tool calls

README 摘要

dsh-dlp Data-loss prevention for DeepSeek Harness, built as an out-of-repo plugin. It does six things: 1. Denies credential-file access and secrets bound for the network — unconditionally, from ctx.tools.guard() . It tests the path-typed arguments of a call against a table of credential stores, following symlinks first. 2. Redacts secrets out of tool results before the model reads them and before the session log records them, and withholds a result it cannot clean. 3. Redacts secrets out of exported telemetry , patching a hole where DSH TELEMETRY MODE=FULL ships message text, tool arguments, tool results and workspace paths in the clear. 4. Strips the invisible characters that carry hidden instructions out of tool results — the Tags block and bidi overrides — and counts the classes it will not touch because they also appear in legitimate text. 5. Neutralises remote markdown images in assistant output , and detects a tool call another plugin rewrote after the session log recorded it. Both are partial mitigations for defects in the harness rather than in your configuration — see below, including what they do not close. 6. Writes an audit record for every decision to its own sink — ru…

在 GitHub 查看完整 README →
Agent/智能体deepseek-harnessdlpdsh-pluginsecret-detectionagent

分类