The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted external data from Jira issues and Confluence pages, which could contain hidden malicious instructions designed to influence the agent's behavior.
Ingestion points: The skill uses mcp__atlassian__getJiraIssue and mcp__atlassian__getConfluencePage in SKILL.md to retrieve markdown content based on user-supplied arguments.
Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are used when incorporating this external content into the agent's context.
Capability inventory: The agent is instructed to perform codebase analysis, including file system navigation and executing git commands.
Sanitization: The skill does not implement any filtering or escaping for the external content retrieved from Atlassian tools.
[COMMAND_EXECUTION]: The skill employs dynamic context injection to execute shell commands at load time.
Evidence: Commands git ls-files, git log -10 --oneline, and git status are executed within SKILL.md. These are benign developer tools used to identify frontend roots and recent activity.

prime-frontend