synap-assistant

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill manages a local knowledge base by executing various synap CLI commands. These operations interact with data files and configurations located in the user's home directory under ~/.config/synap/.
  • [EXTERNAL_DOWNLOADS]: The documentation guides the user to install the synap package from the npm registry if it is not already installed. This package is the intended core component of the skill's functionality.
  • [DATA_EXFILTRATION]: The skill features Git synchronization capabilities (synap sync, synap save) that send user data to remote repositories. This is a documented, intended feature designed for multi-device data persistence.
  • [PROMPT_INJECTION]: Processing user-generated content from knowledge entries creates an indirect prompt injection surface.
  • Ingestion points: Content is ingested from entries.json, archive.json, and user-preferences.md through commands such as synap list --json and synap show.
  • Boundary markers: The instructions do not define delimiters or other boundary markers to isolate user-provided entry content from agent instructions during triage or review.
  • Capability inventory: The agent has the ability to delete entries (synap delete), modify system preferences (synap preferences set), and initiate network synchronization via Git.
  • Sanitization: No content sanitization or instruction-filtering mechanisms are mentioned for processing ingested data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 11:55 PM
Security Audit — agent-trust-hub — synap-assistant