Historial de auditorías - ai-partner-chat

Versión de auditoría 5

Más reciente Riesgo bajo

Jan 17, 2026, 12:32 AM

After detailed analysis, this is a legitimate AI learning companion skill. All static findings are false positives: backticks are documentation examples, cryptographic patterns are benign tech lists, hidden file access is standard Claude Code skill storage, and SQLite/ChromaDB operations are intended local persistence. No malicious intent or credential exfiltration detected.

22

Archivos escaneados

5,716

Líneas analizadas

2

hallazgos

claude

Auditado por

No se encontraron problemas de seguridad

Factores de riesgo

📁 Acceso al sistema de archivos (3)

scripts/conversation_logger.py:62 scripts/note_processor.py:49 scripts/vector_indexer.py:104

⚡ Contiene scripts (2)

scripts/emotion_analyzer.py:17 scripts/orchestrator.py:29

Versión de auditoría 4

Riesgo bajo

Jan 17, 2026, 12:32 AM

After detailed analysis, this is a legitimate AI learning companion skill. All static findings are false positives: backticks are documentation examples, cryptographic patterns are benign tech lists, hidden file access is standard Claude Code skill storage, and SQLite/ChromaDB operations are intended local persistence. No malicious intent or credential exfiltration detected.

22

Archivos escaneados

5,716

Líneas analizadas

2

hallazgos

claude

Auditado por

No se encontraron problemas de seguridad

Factores de riesgo

📁 Acceso al sistema de archivos (3)

scripts/conversation_logger.py:62 scripts/note_processor.py:49 scripts/vector_indexer.py:104

⚡ Contiene scripts (2)

scripts/emotion_analyzer.py:17 scripts/orchestrator.py:29

Versión de auditoría 3

Riesgo bajo

Jan 10, 2026, 01:08 PM

Legitimate AI learning assistant skill with local data storage. All data stays on user's machine via ChromaDB. Network access only for downloading embedding model from HuggingFace.

17

Archivos escaneados

3,580

Líneas analizadas

5

hallazgos

claude

Auditado por

Problemas de riesgo bajo (2)

scripts/note_processor.py:59-77

Filesystem access to user notes directory

The skill scans project 'notes/' directory to process markdown files. This is expected behavior for a note processing skill. Access is limited to notes directory within projects where the skill is activated.

scripts/vector_indexer.py:85-96

Model download from HuggingFace

The BAAI/bge-m3 embedding model (~4.3GB) is downloaded from HuggingFace on first run. This is documented and necessary for vector embeddings. Model cached locally for subsequent runs.

Factores de riesgo

📁 Acceso al sistema de archivos (2)

scripts/note_processor.py:59-77 scripts/orchestrator.py:54-59

🌐 Acceso a red (1)

scripts/vector_indexer.py:85-96

⚡ Contiene scripts (1)

install.sh:1-130

Versión de auditoría 2

Riesgo bajo

Jan 10, 2026, 01:08 PM

Legitimate AI learning assistant skill with local data storage. All data stays on user's machine via ChromaDB. Network access only for downloading embedding model from HuggingFace.

17

Archivos escaneados

3,580

Líneas analizadas

5

hallazgos

claude

Auditado por

Problemas de riesgo bajo (2)

scripts/note_processor.py:59-77

Filesystem access to user notes directory

The skill scans project 'notes/' directory to process markdown files. This is expected behavior for a note processing skill. Access is limited to notes directory within projects where the skill is activated.

scripts/vector_indexer.py:85-96

Model download from HuggingFace

The BAAI/bge-m3 embedding model (~4.3GB) is downloaded from HuggingFace on first run. This is documented and necessary for vector embeddings. Model cached locally for subsequent runs.

Factores de riesgo

📁 Acceso al sistema de archivos (2)

scripts/note_processor.py:59-77 scripts/orchestrator.py:54-59

🌐 Acceso a red (1)

scripts/vector_indexer.py:85-96

⚡ Contiene scripts (1)

install.sh:1-130

Versión de auditoría 1

Riesgo bajo

Jan 10, 2026, 01:08 PM

Legitimate AI learning assistant skill with local data storage. All data stays on user's machine via ChromaDB. Network access only for downloading embedding model from HuggingFace.

17

Archivos escaneados

3,580

Líneas analizadas

5

hallazgos

claude

Auditado por

Problemas de riesgo bajo (2)

scripts/note_processor.py:59-77

Filesystem access to user notes directory

The skill scans project 'notes/' directory to process markdown files. This is expected behavior for a note processing skill. Access is limited to notes directory within projects where the skill is activated.

scripts/vector_indexer.py:85-96

Model download from HuggingFace

The BAAI/bge-m3 embedding model (~4.3GB) is downloaded from HuggingFace on first run. This is documented and necessary for vector embeddings. Model cached locally for subsequent runs.

Factores de riesgo

📁 Acceso al sistema de archivos (2)

scripts/note_processor.py:59-77 scripts/orchestrator.py:54-59

🌐 Acceso a red (1)

scripts/vector_indexer.py:85-96

⚡ Contiene scripts (1)

install.sh:1-130