The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external code provided via the Read and Grep tools, creating an attack surface for indirect prompt injection if the analyzed files contain malicious instructions.
Ingestion points: External code files, modules, or pull requests specified in the skill arguments and accessed through the Read and Grep tools.
Boundary markers: Not explicitly defined within the skill instructions; reliance is placed on the underlying agent's handling of tool outputs.
Capability inventory: The skill is limited to Read and Grep operations, posing minimal risk of downstream command execution or data exfiltration.
Sanitization: No specific sanitization or escaping of the ingested code content is performed before it is processed by the agent.

code-evolution