The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources which could potentially contain malicious instructions aimed at influencing the agent's behavior.
Ingestion points: The skill fetches external content using gh issue view and reads local plan files (e.g., docs/plans/*.md) which may contain user-generated or external content.
Boundary markers: There are no explicit instructions to wrap this external content in delimiters or to use safety warnings to ignore embedded instructions.
Capability inventory: The skill has broad capabilities including arbitrary shell command execution via the Bash tool and the ability to modify any file using Write and Edit tools.
Sanitization: The skill does not perform sanitization or validation on the fetched text before using it to determine its implementation steps.
[COMMAND_EXECUTION]: The skill dynamically discovers and executes build, test, and lint commands defined within the repository's configuration files (such as package.json, Makefile, or pyproject.toml). While this is central to its function, it involves executing commands that are not hardcoded in the skill itself.

implementkit