ai-automation-workflows
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill demonstrates a pattern for processing local data files by interpolating their content directly into AI prompts. This creates a surface for indirect prompt injection if the files contain malicious instructions.
- Ingestion points:
SKILL.md(Data Processing Pipeline example) - Boundary markers: Absent (file content is directly concatenated into the prompt string)
- Capability inventory: The skill uses the
infshtool to execute various AI models - Sanitization: Absent
- [COMMAND_EXECUTION]: The skill is designed to execute shell commands via the
infshCLI tool to orchestrate AI tasks. - Evidence: Extensive use of
infshcommands in bash and python scripts for tasks like login, running apps, and managing results. - Context: This is the intended primary purpose of the skill for automation and is considered normal vendor functionality.
Audit Metadata