The Agent Skills Directory

Indirect Prompt Injection (HIGH): The skill is susceptible to indirect prompt injection attacks where malicious instructions are embedded within the React code it analyzes.
Ingestion points: The skill utilizes Read, Grep, and Glob tools to ingest external React source files as defined in the description of SKILL.md.
Boundary markers: There are no defined delimiters or instructions to ignore embedded prompts within the source code being analyzed, making the agent likely to follow instructions found in code comments or strings.
Capability inventory: The skill is granted Write and Edit permissions, enabling it to perform file modifications and potentially propagate malicious code or configuration changes based on untrusted input.
Sanitization: No sanitization or validation logic is present to filter out potential instructions hidden in the processed data.

form-analyzer