draft-landing
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The workflow in SKILL.md executes shell commands via the Bash tool. Specifically, it runs python3 -m draft_agent.uiux search with user-provided arguments.
- [PROMPT_INJECTION]: Indirect prompt injection vulnerability identified in SKILL.md. The variable {product_type} is taken directly from the user's request and inserted into a shell command. * Ingestion points: User input for {product_type} in SKILL.md. * Boundary markers: Missing. The input is wrapped in double quotes in the command template, but this is insufficient to prevent shell injection via subshells or command separators. * Capability inventory: The skill has access to the Bash tool as specified in the allowed-tools section of the frontmatter. * Sanitization: No evidence of input sanitization, escaping, or validation before the variable is used in the python3 command.
Audit Metadata