deepchat-data-import

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill provides detailed instructions for locating and accessing sensitive application data on the local filesystem, including credentials and private message history.
  • It identifies specific sensitive file paths such as ~/Library/Application Support/DeepChat/app_db/agent.db and describes the structure of database-security.json used for encryption management.
  • It provides code snippets for programmatic decryption of application data using Electron's safeStorage.decryptString API.
  • It explicitly targets sensitive fields like providers.api_key, OAuth tokens, and MCP environment variables for extraction.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for ingesting external data from SQLite databases, which presents an attack surface for instructions embedded in the imported content.
  • Ingestion points: Data is read from agent.db and legacy chat.db files, which contain user-generated and potentially external content (SKILL.md, references/data-locations.md).
  • Boundary markers: The instructions lack specific delimiters or "ignore previous instruction" wrappers for the data being imported, though they do recommend redacting secrets (SKILL.md).
  • Capability inventory: The skill facilitates read access to the local filesystem and database operations on specific application data directories (references/sqlite-access.md).
  • Sanitization: There are no documented methods for sanitizing or escaping natural language content found within the database tables before it is processed by the agent (references/import-recipes.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 11:21 AM
Security Audit — agent-trust-hub — deepchat-data-import