The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it processes and displays untrusted data (issue summaries, descriptions, and comments) from Jira.
Ingestion points: The scripts/jira-cli script (functions cmd_view and cmd_list) fetches content from an external API and outputs it to the terminal.
Boundary markers: No delimiters or warnings are used to distinguish external content from system instructions.
Capability inventory: The script uses the requests library to perform network operations against the Jira REST API.
Sanitization: The _extract_text function extracts plain text from the Atlassian Document Format (ADF) but does not sanitize the content for potential LLM instructions.
[SAFE]: Authentication is handled correctly via environment variables (JIRA_EMAIL, JIRA_API_TOKEN), which is the recommended practice for managing secrets in CLI tools.
[SAFE]: Network requests are directed only to the user-specified Jira server (JIRA_SERVER), and the script does not attempt to exfiltrate data to unauthorized third-party domains.

jira-cli