The Agent Skills Directory

[PROMPT_INJECTION]: No instructions were found that attempt to bypass AI safety guardrails or override system prompts.
[DATA_EXFILTRATION]: No unauthorized access to sensitive files or network exfiltration patterns were identified.
[REMOTE_CODE_EXECUTION]: The skill does not attempt to download or execute code from external or untrusted servers.
[PROMPT_INJECTION]: The skill demonstrates an attack surface for indirect prompt injection by reading project documentation, commits, and source code to infer project context. However, the intent is restricted to code generation and review.
Ingestion points: Reads package.json, project documentation, and existing source code files as specified in SKILL.md.
Boundary markers: The instructions do not define specific delimiters to isolate external data from internal logic.
Capability inventory: The skill utilizes file system tools including Read, Glob, Grep, Edit, and Write to perform code analysis and modification tasks.
Sanitization: No input sanitization or validation steps are outlined for the data ingested from the local codebase.

recharts