The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill retrieves ticket information from Jira, which could contain instructions designed to manipulate the agent's behavior.
Ingestion points: Ticket summaries, descriptions, and comments are fetched via tools like jira_get_issue and REST API calls defined in SKILL.md.
Boundary markers: The skill lacks explicit boundary markers or instructions to isolate external Jira data from the agent's core instructions.
Capability inventory: The agent can execute network requests via curl and perform modifications like updating issues and adding comments.
Sanitization: No sanitization logic is provided to filter or escape potentially malicious input within Jira fields.
[EXTERNAL_DOWNLOADS]: The instructions suggest installing the mcp-atlassian package using uvx to provide the Jira integration capabilities.

jira-integration