Skills
skills/roger-235/my_skill_repo/agent-workflow-designer/Gen Agent Trust Hub

agent-workflow-designer

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions in SKILL.md direct the agent to run a local script at scripts/workflow_scaffolder.py. This script is used to generate workflow skeletons but is not included in the provided file set.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection and command argument injection.
  • Ingestion points: User-provided workflow goals, names, and requirements provided in the conversation context.
  • Boundary markers: None identified; the skill does not instruct the agent to use delimiters or ignore instructions embedded within the user input.
  • Capability inventory: The skill performs shell command execution via python3 and file writing via the --output flag as described in the Quick Start section of SKILL.md.
  • Sanitization: None identified; there are no instructions to validate or escape user input before it is used as a command-line argument (e.g., the --name parameter).
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 08:06 PM
Security Audit — agent-trust-hub — agent-workflow-designer