obsidian-clipper-template-creator
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill ingests untrusted data from arbitrary URLs using the
WebFetchtool to identify metadata and CSS selectors. - Ingestion points: Website content retrieved via
WebFetchas described inreferences/analysis-workflow.md. - Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands within the fetched HTML/JSON-LD content.
- Capability inventory: Network read (
WebFetch), local file read (Templates/Bases/*.base), and template generation. - Sanitization: The instructions recommend verifying selectors against the fetched content but do not include specific sanitization or escaping of the retrieved data before it is processed by the agent's reasoning logic.
- [Data Exposure & Exfiltration] (SAFE): The skill reads from a specific directory (
Templates/Bases/) to align with user templates. This is restricted to application-specific files and does not target sensitive system paths or credentials. - [Unverifiable Dependencies & Remote Code Execution] (SAFE): No external package managers or remote script executions were detected in the skill files.
Audit Metadata