The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it ingests untrusted data from Jira issues and interpolates it into templates used for agent reasoning.
Ingestion points: Data is pulled from external sources into the bug_template, feature_template, and epic_template structures defined in SKILL.md (fields like {{description}}, {{user_type}}, and {{overview}}).
Boundary markers: The templates do not utilize specific delimiters or instructions to prevent the agent from following commands that might be hidden within Jira issue descriptions.
Capability inventory: The skill utilizes tools for modifying system state, including jira_create_issue, jira_update_issue, and jira_transition as defined in the frontmatter.
Sanitization: There is no evidence of validation or sanitization of external content before it is processed by the agent.

Jira Automation