The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's primary function involves ingesting untrusted data from the local codebase, which creates a surface for indirect prompt injection attacks.
Ingestion points: The skill reads exported function signatures and implementations from the local codebase using Read, Grep, and Glob tools.
Boundary markers: The instructions lack specific delimiters or explicit safety warnings to the agent to disregard instructions that might be embedded in code comments or string literals within the analyzed files.
Capability inventory: The skill has access to Read, Grep, Glob, and Bash tools, providing a path for potential command execution if the agent is successfully injected via the processed code.
Sanitization: No sanitization, filtering, or validation of the ingested code content is described before the data is processed by the agent.

codebase-hygiene