The Agent Skills Directory

[Indirect Prompt Injection] (HIGH): The skill facilitates the analysis of external codebases and provides the agent with tools to modify files, which is a high-risk configuration for indirect injection.
Ingestion points: The skill utilizes Read, Grep, and Glob tools to ingest React component code from the environment.
Boundary markers: There are no boundary markers or explicit instructions to ignore embedded commands within the analyzed code.
Capability inventory: The Write and Edit tools allow for permanent modification of the local filesystem, which could be subverted by instructions hidden in external data.
Sanitization: No sanitization or validation of the ingested code is performed.
[No Code] (LOW): The skill contains no executable logic or scripts and relies entirely on natural language instructions and agent-provided tools.

error-analyzer