The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The scripts/setup file installs jq and ankitpokhrel/jira-cli using Homebrew. These are well-known technology tools and the installation method is a standard practice for macOS environments.
[CREDENTIALS_UNSAFE]: The skill manages sensitive Atlassian API tokens. However, it implements protective measures by storing them in ~/.atlassian-env with restricted permissions (chmod 600) and automatically adding the file to the global git configuration's excludes list to prevent accidental exposure in repositories.
[PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks common to data-retrieval tools.
Ingestion points: Untrusted data enters the agent context through confluence get, confluence search, jira issue view, and jira issue list operations in scripts/confluence and scripts/jira.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the scripts when presenting retrieved content to the agent.
Capability inventory: The skill possesses the capability to execute subprocesses and perform network operations via curl and the jira CLI.
Sanitization: There is no evidence of sanitization or filtering of the content retrieved from Atlassian services before it is passed to the agent's context.

atlassian