The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the run_command tool to execute git diff --staged to retrieve local code changes for analysis.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) as it processes untrusted data from Jira tickets.
Ingestion points: Summary and Description fields are retrieved via mcp_atlassian-mcp-server_getJiraIssue in SKILL.md.
Boundary markers: No delimiters or protective instructions are used to separate ticket data from agent instructions.
Capability inventory: The skill has access to the run_command tool and the mcp_atlassian-mcp-server_addCommentToJiraIssue tool.
Sanitization: There is no evidence of sanitization or validation of the content retrieved from Jira.

jira-bug