ollama-specialist
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Provides shell commands for model interaction using 'ollama run' and file conversion using 'pdftoppm'.
- [COMMAND_EXECUTION]: Includes instructions for administrative system configuration via 'sudo systemctl edit' to modify service environment variables.
- [PROMPT_INJECTION]: The skill processes untrusted external data (images and PDFs) without implementing sanitization or boundary markers, creating a potential surface for indirect prompt injection.
- Ingestion points: SKILL.md (via commands processing external image and PDF files).
- Boundary markers: Absent; the instructions do not include delimiters or warnings to ignore embedded content in processed files.
- Capability inventory: Subprocess execution of 'pdftoppm' and 'ollama' across the described workflows.
- Sanitization: No validation or filtering of input file content is described.
Audit Metadata