obsidian-clipper-template-creator

Pass

Audited by Gen Agent Trust Hub on Apr 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes the WebFetch tool to retrieve data from user-provided external URLs. This is used to analyze HTML structure, meta tags, and Schema.org data for template generation.
  • [COMMAND_EXECUTION]: The skill performs local file system read operations within the Templates/Bases/ directory to identify user-defined schemas (e.g., Recipes.base). While limited to a specific path, this involves accessing local vault data.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests and analyzes untrusted data from the web (HTML, scripts, and metadata).
  • Ingestion points: Web content retrieved via WebFetch as described in references/analysis-workflow.md.
  • Boundary markers: The instructions do not specify any delimiters or safety warnings to ignore instructions found within the fetched external content.
  • Capability inventory: The agent can perform network reads (WebFetch), read local files (Templates/Bases/), and generate structured JSON output.
  • Sanitization: There is no evidence of sanitization or filtering applied to the retrieved content before the agent processes it for analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 11, 2026, 06:19 PM
Security Audit — agent-trust-hub — obsidian-clipper-template-creator