The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it facilitates code generation based on potentially untrusted external inputs while having access to powerful tools.
Ingestion points: The skill allows for the processing of user-provided requirements and data fetched via the WebSearch and Read tools (specified in SKILL.md).
Boundary markers: The SKILL.md file does not define specific delimiters or instructions to prevent the agent from obeying instructions embedded within the data it processes.
Capability inventory: The skill environment includes Bash, Write, Edit, and WebSearch capabilities as defined in the allowed-tools section of SKILL.md.
Sanitization: There are no documented mechanisms within the skill to sanitize or validate external content before it is interpolated into the agent's context or used to generate code.

react-coder