The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external data that could contain hidden instructions targeting the AI agent.
Ingestion points: The chunk build-prompt command (referenced in references/chunk-cli.md) generates context for the AI by reading GitHub pull request comments.
Capability inventory: The skill is capable of executing shell commands via the chunk CLI, including chunk task run, chunk validate, and environment setup actions.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the data ingested from GitHub.
Sanitization: There is no mention of filtering or sanitizing the input retrieved from external GitHub comments before it is processed by the AI.
[EXTERNAL_DOWNLOADS]: The skill directs the user to download a CLI tool from a remote repository.
Evidence: The installation command brew install CircleCI-Public/circleci/chunk fetches the tool from the official CircleCI-Public GitHub organization. This is a vendor-owned resource matching the skill's author.
[COMMAND_EXECUTION]: The skill requires the execution of multiple shell commands to set up and use the Chunk tool.
The agent is instructed to perform actions such as chunk auth login, chunk init, chunk validate, and chunk task run to manage CI/CD workflows and sandbox environments.

chunk