obsidian-clipper-template-creator
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a vulnerability to indirect prompt injection by processing external content.\n
- Ingestion points: Untrusted data enters the agent context via the
WebFetchtool, which retrieves HTML and JSON content from user-provided URLs as referenced inreferences/analysis-workflow.md.\n - Boundary markers: The skill lacks explicit boundary markers or delimiters to isolate fetched content from its own instructions, and it does not provide warnings to the agent to ignore instructions embedded in the external data.\n
- Capability inventory: The agent has the capability to read local template files in
Templates/Bases/, execute web requests viaWebFetch, and generate structured JSON output.\n - Sanitization: No sanitization, escaping, or validation of the fetched web content is performed before it is analyzed by the agent.
Audit Metadata