The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected in the skill scripts or instructions. The skill focuses on legitimate Angular framework best practices such as standalone components and signals.
[COMMAND_EXECUTION]: The skill instructions include a memory protocol that uses the shell command 'cat .claude/context/memory/learnings.md'. This is a benign operation used to maintain context between sessions in compatible agent environments.
[PROMPT_INJECTION]: The skill processes project files and user-provided code which are surfaces for indirect prompt injection. 1. Ingestion points: Project files read via Read, Grep, and Glob tools. 2. Boundary markers: No explicit markers are defined to isolate untrusted data from the agent's instructions. 3. Capability inventory: The agent has access to file modification and shell execution via Write, Edit, and Bash tools. 4. Sanitization: No sanitization or validation of the data ingested from files is performed before processing.

angular-expert