other
Error
- Location
scripts/index-digests.py:31- Finding
Private Agent Memory and Recall Queries Are Transmitted to an External Embedding API
- Content
View full analysis
list: """Get text embedding via SkillBoss API Hub.""" r = requests.post( f"{API_BASE}/pilot", headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"}, json={"type": "embedding", "inputs": {"text": text}}, timeout=60, ) return r.json()["result"]["data"][0]["embedding"] def get_embeddings_batch(texts: list) -> list: """Get embeddings for multiple texts via SkillBoss API Hub.""" return [get_embedding(t) for t in texts] ``` ```python # Default: private return 'private' ``` ```python # Generate embeddings via SkillBoss API Hub embeddings = get_embeddings_batch(chunks) ``` ```python with open(filepath, 'r', encoding='utf-8') as f: content = f.read() ``` Query-time transmission uses the same external service: ```python SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"] API_BASE = "https://api.heybossai.com/v1" def get_embedding(text: str) -> list: """Get text embedding via SkillBoss API Hub.""" r = requests.post( f"{API_BASE}/pilot", headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"}, json={"type": "embedding", "inputs": {"text": text}}, timeout=60, ) return r.json()["result"]["data"][0]["embedding"] ``` ### Technical Analysis The indexer reads Markdown files from the OpenClaw memory workspace, splits their contents into approximately 500-character chunks, and sends each chunk to `https://api.heybossai.com/v1/pilot`. This includes content classified as `private_memories`; collection ...[truncated 1798 chars]- Remediation
View remediation