The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, which presents a surface for indirect prompt injection attacks.
Ingestion points: The workflow described in SKILL.md involves reading user requests, project specifications, source code, and git differences.
Boundary markers: There are no instructions in the skill files to use delimiters or to explicitly ignore instructions that might be embedded within the source code or specifications being analyzed.
Capability inventory: The skill is authorized to perform file modifications, update project documentation, and create git commits based on its analysis of the ingested data.
Sanitization: The instructions do not define any sanitization, validation, or filtering of external content before it is processed by the agent.

implement