Commit Graph

5 Commits

Author SHA1 Message Date
Sharang Parnerkar
da4084ee78 feat: refine all LLM system prompts for precision and reduced false positives
Some checks failed
CI / Check (pull_request) Successful in 10m8s
CI / Detect Changes (pull_request) Has been skipped
CI / Deploy Agent (pull_request) Has been cancelled
CI / Deploy Dashboard (pull_request) Has been cancelled
CI / Deploy Docs (pull_request) Has been cancelled
CI / Deploy MCP (pull_request) Has been cancelled
Code review prompts (review_prompts.rs):
- Add explicit "Do NOT report" sections listing common false positive patterns
- Add language-specific guidance (Rust short-circuit, shadowing, clone patterns)
- Cap findings per pass (3 for conventions, 2 for complexity) to reduce noise
- Raise complexity thresholds (80 lines, 5+ nesting) to pragmatic levels
- Require concrete bug scenarios, not theoretical concerns
- Separate severity guides per pass with clear definitions

Triage prompt (triage.rs):
- Add explicit dismiss criteria for language idioms, non-security hash usage,
  operational logging, and duplicate findings
- Add confirm-only-when criteria requiring concrete exploit scenarios
- Refined confidence scoring guide with clear thresholds

Finding descriptions (descriptions.rs):
- Rewrite to be developer-facing: lead with what/where, skip filler
- Fix suggestions should show corrected code, not vulnerable code
- Remove generic "could lead to" phrasing in favor of specific scenarios

Code fix suggestions (fixes.rs):
- Require drop-in replacement code preserving original style
- Handle false positives by returning original code with explanation
- Limit inline comments to the changed line only

Pentest orchestrator (prompt_builder.rs):
- Add "Finding Quality Rules" section preventing duplicate findings
- Instruct grouping related findings (e.g. missing headers = one finding)
- Cap missing header severity at medium unless exploit demonstrated
- Mark console.log in vendored/minified JS as informational only

RAG chat (chat.rs):
- Add concise rules for referencing files/lines and security context

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-29 22:57:37 +02:00
Sharang Parnerkar
99983c51e3 feat: enhance tracing with field attributes and warn logging across all handlers
All checks were successful
CI / Tests (push) Successful in 5m17s
CI / Detect Changes (push) Successful in 3s
CI / Deploy Agent (push) Successful in 3s
CI / Deploy Dashboard (push) Has been skipped
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Has been skipped
CI / Format (push) Successful in 4s
CI / Clippy (push) Successful in 4m38s
CI / Security Audit (push) Successful in 1m50s
Add repo_id, finding_id, and filter fields to tracing::instrument attributes
for better trace correlation in SigNoz. Replace all silently swallowed errors
(Err(_) => Vec::new()) with tracing::warn! logging across mod.rs, dast.rs,
graph.rs handlers. Add stage-level spans with .instrument() to pipeline
orchestrator for visibility into scan phases.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-10 21:56:16 +01:00
Sharang Parnerkar
67d6a937ae feat: add OpenTelemetry trace spans to all handlers and pipeline functions
All checks were successful
CI / Clippy (push) Successful in 4m26s
CI / Security Audit (push) Successful in 1m46s
CI / Format (push) Successful in 4s
CI / Tests (push) Successful in 5m16s
CI / Detect Changes (push) Successful in 4s
CI / Deploy Agent (push) Successful in 3s
CI / Deploy Dashboard (push) Has been skipped
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Has been skipped
Add #[tracing::instrument(skip_all)] to 44 functions:
- 19 API handlers in mod.rs
- 3 chat handlers, 6 DAST handlers, 7 graph handlers
- 2 pipeline orchestrator functions
- 7 scanner functions (sbom, semgrep, gitleaks, cve, lint, patterns)

This generates trace spans for SigNoz visibility into request
latency, scan pipeline stages, and error tracking.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-10 17:08:13 +01:00
46bf9de549 feat: findings refinement, new scanners, and deployment tooling (#6)
Some checks failed
CI / Format (push) Successful in 3s
CI / Clippy (push) Successful in 4m3s
CI / Security Audit (push) Successful in 1m38s
CI / Tests (push) Successful in 4m44s
CI / Detect Changes (push) Successful in 2s
CI / Deploy Agent (push) Successful in 2s
CI / Deploy Dashboard (push) Successful in 2s
CI / Deploy Docs (push) Has been skipped
CI / Deploy MCP (push) Failing after 2s
2026-03-09 12:53:12 +00:00
42cabf0582 feat: rag-embedding-ai-chat (#1)
All checks were successful
CI / Format (push) Successful in 2s
CI / Clippy (push) Successful in 2m56s
CI / Security Audit (push) Successful in 1m25s
CI / Tests (push) Successful in 3m57s
Co-authored-by: Sharang Parnerkar <parnerkarsharang@gmail.com>
Reviewed-on: #1
2026-03-06 21:54:15 +00:00