The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to create logic that interacts with untrusted Jira issue data, such as descriptions and comments. However, the attack surface is limited to logic manipulation within the Jira workflow, as the language itself is sandboxed.
Ingestion points: The skill references data from issue.description, issue.comments, and custom fields as seen in references/examples.md.
Boundary markers: No specific boundary markers or delimiters for untrusted input are provided; however, the skill mandates strict type and null checking.
Capability inventory: The Jira Expressions DSL documented in references/reference.md has no support for network operations, file system access, or OS-level command execution.
Sanitization: The skill does not provide methods for sanitizing data against prompt injection, relying on the platform's restricted execution environment.
[SAFE]: The skill contains no evidence of obfuscation, persistence mechanisms, or unauthorized privilege escalation. It provides standard instructional content for Jira administrators.

jira-expressions