The Agent Skills Directory

[Indirect Prompt Injection] (HIGH): The skill is designed to ingest untrusted user requirements and generate code/configurations while having access to high-privilege tools like Bash, Write, and Edit.
Ingestion points: User requests containing "acceptance criteria creator" or enterprise workflow patterns (SKILL.md).
Boundary markers: None present to distinguish between instructions and data.
Capability inventory: Access to Bash, Read, Write, and Edit tools (SKILL.md frontmatter).
Sanitization: No sanitization or validation logic is defined to prevent instructions embedded in requirements from being executed by the tools.
[Command Execution] (HIGH): The skill explicitly requests Bash access. Given the purpose of generating "production-ready code and configurations," an attacker could use indirect prompt injection to trick the agent into executing arbitrary shell commands under the guise of setting up a workflow.

acceptance-criteria-creator