The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external source code and identifiers to provide naming guidance and perform renames, creating a surface for indirect prompt injection if the processed files contain malicious instructions.
Ingestion points: Reads source code files (e.g., .ts, .tsx, .py, .md) using the Read and Grep tools to identify names and call sites.
Boundary markers: None present; the instructions do not explicitly tell the agent to ignore instructions embedded within the code it analyzes.
Capability inventory: The skill uses Edit to perform renames and Bash to execute grep commands for finding identifier references.
Sanitization: No specific sanitization or validation of the input source code is defined within the skill instructions.

naming-conventions