CyberSecurityUP e4f6b42f37 feat(harness): add MCP hot-reload, reference prompts, and agent autonomy levels ...

- mcp_hot_reload.rs: watches mcp.servers.json for mid-run changes,
  rewrites .mcp.json so next agent spawn picks up new MCP servers
  (e.g. Playwright) without restarting the engagement. Includes
  add_server/remove_server helpers for REPL integration.

- reference_prompts: new RunConfig field accepting paths to .md files
  (e.g. pentest methodology guides) injected into every agent prompt
  as supplementary testing material (capped at 8000 chars each).

- autonomy levels: "cautious", "standard", "aggressive", "full" —
  shape how aggressively agents explore. Higher levels encourage
  creative lateral testing, tool installs, WAF bypasses, zero-day
  hunting, and exhaustive business logic exploration.

2026-10-18 22:28:26 -03:00

..

agents_md/mobile

feat(mobile): binary/APK/IPA testing mode + 12 RE skills — v4.2.0

2026-09-20 21:08:14 -03:00

app

release: v4.3.3 — per-finding attack path, LLM config modal, severity badges

2026-10-16 17:26:42 -03:00

crates/harness

feat(harness): add MCP hot-reload, reference prompts, and agent autonomy levels

2026-10-18 22:28:26 -03:00

templates

fix(web+report): treat needs-review findings as validated findings

2026-10-18 16:54:49 -03:00

tools

feat(decision): pluggable System One backend — TypeSafe (hosted) or Laya (local)

2026-09-20 19:27:14 -03:00

.gitignore

chore: remove test artifacts, ignore scan debris (#35)

2026-07-31 15:39:00 -03:00

Cargo.lock

feat(harness): add MCP hot-reload, reference prompts, and agent autonomy levels

2026-10-18 22:28:26 -03:00

Cargo.toml

chore: bump version to v4.4.0 and update README with resilience features

2026-10-18 19:52:51 -03:00

creds.example.yaml

docs: full creds.yaml reference (web/multi-role/ssh/windows/cloud) in TUTORIAL + example file

2026-07-02 08:44:00 -03:00