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
Risk Level
SAFE
Analyzed
May 15, 2026, 12:37 PM
Security Audit — agent-trust-hub — ollama-specialist