The Agent Skills Directory

[DATA_EXFILTRATION]: Accesses sensitive authentication data stored in ~/.hermes/mcp-tokens/linear.json and repository metadata in ~/.claude/afk.json. This information is used to authenticate requests to the Linear MCP and GitHub APIs.
[PROMPT_INJECTION]: The skill processes untrusted content from issue titles, bodies, and comments provided by external trackers (Linear, GitHub). * Ingestion points: gh issue view, get_issue, and list_comments tool calls in SKILL.md and referenced scripts. * Boundary markers: The instructions lack explicit boundary markers or directives to ignore instructions embedded in the external issue data. * Capability inventory: Includes shell command execution via git and gh, file system operations (reading and writing files), and dispatching tasks to subagents. * Sanitization: No sanitization or validation of the ingested ticket content is performed before processing.
[COMMAND_EXECUTION]: Spawns subprocesses to execute git and gh (GitHub CLI) commands for branch management and PR creation, and uses bun to run TypeScript scripts for Linear integration.

engineer