process-clippings
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes untrusted data from external web clippings.
- Ingestion points: The skill reads content from markdown files in the
Clippings/directory usingobsidian read path="Clippings/<file>.md". - Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the clipping content.
- Capability inventory: The skill uses the
Bashtool to execute file system operations including reading, appending, moving, and deleting files via theobsidianCLI tool. - Sanitization: No sanitization or validation of the clipping content is performed before the agent extracts and integrates information into the Second Brain.
Audit Metadata