中文 EN

Scan Report

Scan New Files

⚠ Low Risk — Risk Score 20/100
Last scan:23 hr ago Rescan
20 /100
agi-evolution-model
基于双环架构的AGI进化模型，通过意向性分析、人格层映射和元认知检测实现持续自我演进
This is a legitimate AGI personality evolution model skill with no malicious behavior. Minor concern: the perception_node.py calculator uses eval() on untrusted input, which is a code injection risk if the tool is exposed to untrusted callers.
Skill Nameagi-evolution-model
Duration50.9s
Enginepi
✓
Safe to install
Consider replacing eval() in the calculator tool with a safer expression evaluator (e.g., ast.literal_eval or a math expression parser). No other security concerns identified; the skill's functionality aligns with its documentation.

Findings 3 items

Severity Finding Location
Medium
Unsafe eval() usage in calculator tool RCE
The calculator tool in perception_node.py uses Python's eval() on the expression parameter without input sanitization. While the tool is currently a mock (returns empty results), if implemented with real functionality and exposed to untrusted callers, it could allow arbitrary code execution.
result = eval(expression)
→ Replace eval() with ast.literal_eval or a safe expression evaluator library that only supports mathematical operations.
 scripts/perception_node.py:474
Low
Optional unsigned C extension loading Supply Chain
Multiple scripts (personality_layer_pure.py, perception_node.py) attempt to load .so/.pyd binaries from local personality_core/ directories. While graceful fallback to Python exists, loading unsigned native binaries from disk carries inherent risk.
import personality_core
→ Verify the integrity of any pre-compiled .so/.pyd files. Consider providing checksums in documentation for users to verify.
 scripts/personality_layer_pure.py:43
Low
SKILL.md uses Bash directive but only calls Python scripts Doc Mismatch
SKILL.md dependency section declares 'system: mkdir -p ./agi_memory' but the primary execution mechanism is python3 subprocess calls. This is a minor documentation imprecision rather than a security violation.
dependency:
  python: []
  system:
    - mkdir -p ./agi_memory
→ Document the python3 script execution chain in the dependency section for completeness.
 SKILL.md:3
ResourceDeclaredInferredStatusEvidence
Filesystem WRITE WRITE ✓ Aligned SKILL.md declares mkdir -p ./agi_memory; scripts write personality.json to ./agi…
Shell WRITE WRITE ✓ Aligned SKILL.md declares python3 scripts/* execution for initialization and personality…
Network NONE NONE — No actual network requests in code; URLs in documentation are static references …
Environment NONE NONE — No os.environ iteration or credential access found
Skill Invoke NONE NONE — No cross-skill invocation patterns found
Clipboard NONE NONE — No clipboard access detected
Browser NONE NONE — No browser automation found
Database NONE NONE — No database access; uses local JSON files only
11 findings
🔗
Medium External URL 外部 URL
https://en.wikipedia.org/wiki/Tf%E2%80%93idf
references/cognitive-insight-v2-implementation.md:1220
🔗
Medium External URL 外部 URL
https://en.wikipedia.org/wiki/Cache_replacement_policies#LRU
references/cognitive-insight-v2-implementation.md:1221
🔗
Medium External URL 外部 URL
https://en.wikipedia.org/wiki/Moving_average#Exponential_moving_average
references/cognitive-insight-v2-implementation.md:1222
🔗
Medium External URL 外部 URL
https://www.gnu.org/licenses/agpl-3.0.html
references/cognitive-insight-v2-implementation.md:1223
🔗
Medium External URL 外部 URL
https://storage.example.com/reports/report.pdf?signature=...
references/tool_use_spec.md:625
🔗
Medium External URL 外部 URL
https://docs.example.com/migration/weather-v1-to-v2
references/tool_use_spec.md:956
🔗
Medium External URL 外部 URL
https://platform.openai.com/docs/guides/function-calling
references/tool_use_spec.md:2137
🔗
Medium External URL 外部 URL
https://docs.anthropic.com/en/docs/tool-use
references/tool_use_spec.md:2138
🔗
Medium External URL 外部 URL
https://modelcontextprotocol.io/
references/tool_use_spec.md:2139
🔗
Medium External URL 外部 URL
https://json-schema.org/
references/tool_use_spec.md:2140
🔗
Medium External URL 外部 URL
https://html.spec.whatwg.org/multipage/server-sent-events.html
references/tool_use_spec.md:2141

File Tree

45 files · 732.9 KB · 21607 lines
Python 26f · 11667L Markdown 18f · 9817L JSON 1f · 123L
├─ ▾ 📁 assets
│ └─ 📋 personality_template.json JSON 123L · 4.1 KB
├─ ▾ 📁 references
│ ├─ 📝 architecture.md Markdown 1331L · 50.0 KB
│ ├─ 📝 c_extension_usage.md Markdown 128L · 3.0 KB
│ ├─ 📝 capability_boundaries.md Markdown 118L · 4.5 KB
│ ├─ 📝 cognitive-architecture-insight-module.md Markdown 330L · 11.9 KB
│ ├─ 📝 cognitive-insight-quick-reference.md Markdown 227L · 7.0 KB
│ ├─ 📝 cognitive-insight-v2-implementation.md Markdown 1227L · 32.7 KB
│ ├─ 📝 information-flow-main-loop.md Markdown 358L · 20.4 KB
│ ├─ 📝 information-flow-overview.md Markdown 301L · 12.4 KB
│ ├─ 📝 information-flow-secondary-loop.md Markdown 467L · 20.4 KB
│ ├─ 📝 init_dialogue_optimized_guide.md Markdown 371L · 11.1 KB
│ ├─ 📝 intentionality_architecture.md Markdown 563L · 16.2 KB
│ ├─ 📝 maslow_needs.md Markdown 160L · 4.4 KB
│ ├─ 📝 metacognition-check-component.md Markdown 610L · 30.2 KB
│ ├─ 📝 metacognition-enhancement-guide.md Markdown 492L · 12.6 KB
│ ├─ 📝 personality_mapping.md Markdown 161L · 5.6 KB
│ ├─ 📝 stratified-storage-design.md Markdown 323L · 10.6 KB
│ └─ 📝 tool_use_spec.md Markdown 2156L · 56.3 KB
├─ ▾ 📁 scripts
│ ├─ 🐍 advice_pool.py Python 469L · 14.9 KB
│ ├─ 🐍 cognitive_insight_backup.py Python 610L · 25.2 KB
│ ├─ 🐍 cognitive_insight_help.py Python 300L · 12.1 KB
│ ├─ 🐍 cognitive_insight.py Python 565L · 20.9 KB
│ ├─ 🐍 concept_extraction_extension.py Python 761L · 25.3 KB
│ ├─ 🐍 data_lifecycle_manager.py Python 389L · 13.4 KB
│ ├─ 🐍 history_manager.py Python 229L · 7.4 KB
│ ├─ 🐍 init_dialogue_optimized.py Python 464L · 16.4 KB
│ ├─ 🐍 intentionality_analyzer.py Python 366L · 12.8 KB
│ ├─ 🐍 intentionality_classifier.py Python 388L · 13.8 KB
│ ├─ 🐍 intentionality_collector.py Python 308L · 9.7 KB
│ ├─ 🐍 intentionality_regulator.py Python 438L · 15.1 KB
│ ├─ 🐍 intentionality_trigger.py Python 592L · 19.9 KB
│ ├─ 🐍 learning_stage_tracker.py Python 274L · 7.9 KB
│ ├─ 🐍 memory_store_pure.py Python 402L · 12.0 KB
│ ├─ 🐍 metacognition_history.py Python 502L · 16.3 KB
│ ├─ 🐍 objectivity_evaluator.py Python 458L · 16.4 KB
│ ├─ 🐍 perception_node.py Python 808L · 26.9 KB
│ ├─ 🐍 personality_core_pure.py Python 144L · 4.4 KB
│ ├─ 🐍 personality_customizer.py Python 675L · 24.0 KB
│ ├─ 🐍 personality_layer_pure.py Python 951L · 32.2 KB
│ ├─ 🐍 show_help.py Python 169L · 4.7 KB
│ ├─ 🐍 strategy_selector.py Python 468L · 15.5 KB
│ ├─ 🐍 test_metacognition_integration.py Python 305L · 9.4 KB
│ ├─ 🐍 test_perception_node.py Python 300L · 9.2 KB
│ └─ 🐍 transcendence_keeper.py Python 332L · 11.7 KB
└─ 📝 SKILL.md Markdown 494L · 21.9 KB

Dependencies 1 items

PackageVersionSourceKnown VulnsNotes
None (Python standard library only) N/A stdlib No No external pip/npm/cargo dependencies. Uses only Python built-in modules: json, os, sys, tempfile, time, datetime, argparse, shutil, uuid, hashlib, logging, typing, dataclasses, enum, functools, collections, re

Security Positives

✓ No credential harvesting or sensitive file access (no ~/.ssh, ~/.aws, .env scanning)
✓ No data exfiltration, C2 communication, or external IP connections
✓ No obfuscation techniques (no base64, atob, or anti-analysis patterns)
✓ No reverse shell, RCE, or remote code execution payloads
✓ Uses only Python standard library — no external dependencies
✓ Atomic file writes with temp file + rename pattern prevents data corruption
✓ Documentation accurately describes core functionality and architecture
✓ C extension loading gracefully falls back to pure Python implementation
✓ File operations are scoped to ./agi_memory directory only
✓ No supply chain risk from unpinned packages — no package manager used