The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands like command -v jira, jira version, and jira configure to manage the tool's lifecycle and verify its availability. These are standard operations for a CLI-based integration.
[EXTERNAL_DOWNLOADS]: The documentation provides instructions for installing the jira-cli tool using well-known and trusted package managers such as Homebrew, apt, and Chocolatey. These sources are considered safe for tool acquisition.
[PROMPT_INJECTION]: The skill is subject to an indirect prompt injection surface because it reads untrusted data from external sources.
Ingestion points: Jira issue descriptions and comment threads are retrieved via the jira issue view command in references/044-planning-jira.md.
Boundary markers: No specific delimiters or boundary markers are defined to isolate the external content from the agent's internal instructions.
Capability inventory: The skill has the ability to execute shell commands and modify Jira issues through the CLI.
Sanitization: There is no evidence of content sanitization or validation before the ingested data is processed for analysis.
[SAFE]: The skill implements strong security practices regarding secrets management. It explicitly instructs the agent never to print or request API tokens in the chat and recommends using system-level secret storage (like macOS Keychain via the security command) instead of environment variables or plain text files.

044-planning-jira