Releases: pikpikcu/airecon
Releases · pikpikcu/airecon
Release list
AIRecon v0.1.7-beta
Significant update introducing MCP Client integration, Interactive Authentication, and major enhancements to agent intelligence, stability, and testing coverage.
✨ New Features
🔌 MCP Client Integration (Issue #45)
- External tool server support via SSE transport
- TUI commands:
/mcp add,/mcp list,/mcp enable,/mcp disable - REST API endpoints for MCP management
- Basic & Bearer authentication support
- Persistent configuration (
~/.airecon/mcp.json) - Async auto-discovery of available tools
🔐 Interactive Authentication (Issue #95)
- CAPTCHA detection & handling (reCAPTCHA, hCaptcha)
- RFC 6238 TOTP generator for 2FA/MFA
- Browser auth state persistence (
save_auth_state,inject_cookies) - LLM-driven interactive input workflow
- OAuth authorization flow support
🧠 Agent Intelligence Enhancements
- OWASP Auto-Tagging: Web Top 10 & API Security classification with severity scoring
- A→B Signal Method: 14 vulnerability signal types for chained discovery
- Response Signature Diffing: Advanced fuzzing validation
- Reflector Agent Pattern: XML error recovery
- Mentor Supervision: Quality control for agent decisions
- Delta-based Objective Patching: Dynamic goal adjustment
📚 Skills Expansion
- 29 new/upgraded skills
- 1089 keywords (+23.2% coverage)
- Major rewrites:
subdomain_enum.md(106→950 lines) - New modules:
- Kubernetes pentesting
- CI/CD attack vectors
- Frida hooking
- Blind XSS
- And more...
🔧 Configuration
No breaking changes. Existing ~/.airecon/config.yaml remains compatible.
New config options:
mcp.json— MCP server configuration- Auth state in session data
🙏 Credits
Full Changelog: v0.1.6-beta...v0.1.7-beta
v0.1.6-beta
What's New in v0.1.6-beta
Phase 1 — Autonomous Recovery & Exploration Engine
- Watchdog forcing — LLM stuck in text-only loop → auto-force
executetool (max 2x before abort) - Anti-stagnation exploration — temperature boost when no new high-confidence evidence (threshold ≥0.65)
- Tool diversity tracking — same-tool streak detection, configurable window and max streak
- Per-phase exploration directives — phase-specific anti-loop tactics injected into system prompt
- Quality scoreboard — evidence 40%, reproducibility 35%, impact 25% weights
- Recovery state context — compact findings injected after every conversation truncation
- Objective queue + evidence log —
objective_queue(max 64),evidence_log(max 200, dedup) - 6 new exploration config keys — full control over exploration behavior in
config.json
Phase 2 — Skill Orchestration & Tool Budget
- Skill phase boost — skills in phase-preferred directories get +2 relevance score
- Tool budget per phase — soft limits per tool per phase (e.g. no
deep_fuzzin RECON) - Budget warnings — 75% (warning), 100% (exhausted), 0 (discouraged) prepended to tool results
- Phase skill hints — active phase lists preferred skill directories in system prompt
Ollama Stability — Context & VRAM Recovery
- Multi-level VRAM crash recovery — 4 escalation tiers via persistent
_adaptive_num_ctx:- Tier 1:
ollama_num_ctx_small, 80 messages, no wait - Tier 2: ÷2 context, 50 messages, 5s wait
- Tier 3: ÷4 context, 30 messages, 10s wait
- Tier 4: 4096 (minimum), 20 messages, 30s wait
- Tier 1:
- Proactive context monitoring — trims conversation at ≥80% token usage (aggressive at ≥90%)
- Dynamic compression interval — 5/10/15 iterations based on context fullness
- OOM-safe compression — skips
compress_with_llmwhen >65% context full - Dynamic tool result cap — scales down with
_adaptive_num_ctxto prevent context overflow - Session auto-saved after each VRAM crash recovery
[CONTEXT MONITOR]hidden from TUI — logged to file only
Tested Endpoints Memory
SessionData.tested_endpoints— LRU list (max 500) tracking"METHOD url"strings- Auto-recorded from
execute(curl + -X/-d detection),browser_action(goto/new_tab), fuzz tools - Shown after truncation — last 20 tested endpoints in critical findings context
@/file and @/folder References
@/pathresolver — copies local files/dirs to Docker workspace/uploads/ automatically- Per-file error handling — single copy errors no longer abort the entire directory operation
- Detailed skip reporting — separates binary, too-large, and OS-error skips in summary
TUI — Slash Command Autocomplete
/prefix triggers slash command autocomplete dropdown in chat inputPathCompleterwidget with proper error logging (no bare except)
Agent Intelligence
- Attack chain detection linking vuln evidence across phases
- Semantic dedup for objectives (Jaccard 0.70 threshold)
- Cross-session memory loading prior findings on start
- Smart fuzzer routing + dynamic URL correlation + injection-chain detection
- 22 new skills added (frameworks, protocols, technologies, LLM coverage)
Version Management
airecon/_version.py— single source of truth for version (all files import from here)install.sh— auto-detects version frompyproject.toml, shows ASCII banner + upgrade diff
Bug Fixes
- Block
$()and backtick command substitution in watchdog (has_dangerous_patterns()) - Auth browser actions:
login_form,handle_totp,save_auth_state,inject_cookies,oauth_authorize _executed_cmd_hashespruned at >5000 entries (memory leak fix)- IDOR false positive reduction in correlation engine
- Phase timeout now counts iterations, not wall-clock time
--ignore-certificate-errorsfor TLS cipher mismatch on pentest targets- 8+ Docker binary name mismatches fixed in
tools_meta.json - All match-breaking issues fixed across pattern files
Tests
- 448 → 879 tests (96% growth)
- New:
test_context_recovery.py,test_tested_endpoints.py,test_recon_dedup.py,test_path_completer.py,test_command_parse.py,test_reporting_helpers.py
Full Changelog: https://github.com/pikpikcu/airecon/blob/main/CHANGELOG.txt
Release v0.1.5-beta
AIRecon v0.1.5-beta Release
Welcome to the v0.1.5-beta release of AIRecon! This update focuses on core stability, race condition fixes, and introducing a comprehensive automated testing suite.
What's Changed
New Contributors
Full Changelog: https://github.com/pikpikcu/airecon/commits/v0.1.5-beta