obsidian-observability

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill implements a debug sidebar panel (DebugView) that displays log history and error messages. This creates a surface for indirect prompt injection if the plugin logs untrusted data.
  • Ingestion points: Logger.log() and ErrorTracker.track() (in SKILL.md) capture arbitrary messages and error objects from plugin operations.
  • Boundary markers: Absent; the DebugView.render() method interpolates message strings directly into DOM elements without delimiters or instructions to the agent to ignore embedded content.
  • Capability inventory: The skill manifest (SKILL.md) specifies Read, Write, Edit, and Bash tools, which could be abused if an agent obeys instructions found in logged data while inspecting the panel.
  • Sanitization: No sanitization, escaping, or filtering is performed on log or error content before it is rendered in the debug view.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 06:47 PM