The Agent Skills Directory

[DYNAMIC_CONTEXT_INJECTION]: The skill uses the ! command syntax to execute shell commands when the skill is loaded. Specifically, it executes git ls-files, git log -10 --oneline, and git status. These commands are standard for project exploration in development environments and do not present a security risk as they are used to identify the backend root and recent activity without exfiltrating sensitive data.
[INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests content from external task management systems and the local codebase. \n
Ingestion points: The skill pulls data from Jira issues and Confluence pages via Atlassian tools and reads local documentation and source files. \n
Boundary markers: The instructions do not define specific delimiters or instructions to prevent the agent from following directions that might be embedded in the ingested content. \n
Capability inventory: The skill's primary capabilities are focused on data retrieval and report generation, which are low-risk activities. \n
Sanitization: No explicit validation or filtering is performed on the data retrieved from external APIs or local files.

prime-backend