The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from project files and git diffs, creating a surface for indirect prompt injection. However, the risk is negligible as the skill lacks write or network capabilities.
Ingestion points: Reads various project files including ARCHITECTURE.md, AGENTS.md, and documentation within docs/ as specified in SKILL.md.
Boundary markers: No explicit boundary markers or isolation instructions are defined for the agent when processing file content.
Capability inventory: The skill is strictly read-only and does not utilize tools for file writing, network requests, or shell execution.
Sanitization: No sanitization or filtering logic is present for the ingested file data.

governance-sync