The Agent Skills Directory

[Indirect Prompt Injection] (LOW): The skill requires the agent to read and follow instructions from various local documentation files (e.g., .claude/skills/shared/angular-design-system.md, docs/design-system/README.md). If these files are compromised or contain malicious instructions, they could influence the agent's behavior.
Ingestion points: The agent is instructed to use Read and Grep on several local markdown and TypeScript files.
Boundary markers: Absent. There are no instructions provided to the agent to distinguish between data and instructions when reading these files.
Capability inventory: The skill has access to Bash, Write, Edit, Grep, and Glob tools, which could be misused if the agent obeys instructions embedded in the documentation.
Sanitization: Absent. No validation or sanitization is performed on the content of the files read.
[Command Execution] (LOW): The skill enables the Bash tool. While necessary for project development tasks like searching (Grep) and file management, it provides a powerful interface that could be exploited if the agent is misled via prompt injection.
[Data Exposure & Exfiltration] (SAFE): No patterns for credential theft, hardcoded secrets, or exfiltration of sensitive system files (e.g., .ssh, .aws) were detected. Access is restricted to the local project directories.

frontend-angular-component