soia-pkm-clip-drive
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill performs file system operations by reading local and cloud document files and writing extracted notes to an Obsidian vault directory.
- [EXTERNAL_DOWNLOADS]: The skill relies on external libraries for text extraction, specifically mentioning pypdf, pdfplumber, and python-docx. It also provides an installation command referencing the vendor's GitHub organization repository.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes content from untrusted external documents that could contain malicious instructions designed to manipulate the agent during the text extraction or summarization phases.
- Ingestion points: External file paths for PDF, Word, and Markdown documents as specified in SKILL.md.
- Boundary markers: None defined for distinguishing extracted text from system instructions.
- Capability inventory: File reading from local/cloud storage and file writing to the Obsidian vault.
- Sanitization: No specific mechanisms described to sanitize or escape extracted document content before it is processed by the agent.
Audit Metadata