The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute various GitHub CLI (gh) commands. These include gh issue list to find configuration and project issues, gh issue view to read project status, and gh issue edit to update the milestone roadmap. These commands are intrinsic to the skill's purpose of project management.- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by reading the body of GitHub issues (labeled tunan:project). Ingestion points: Data is pulled from the body of GitHub issues via gh issue view as described in Phase 0 and the project-issue-contract. Boundary markers: The skill lacks explicit boundary markers or instructions to the agent to ignore embedded commands within the ingested issue body. Capability inventory: The agent has access to the Bash tool (for executing commands), Write (for creating temporary files), and Agent (for calling other skills). Sanitization: There is no evidence of sanitization or filtering applied to the external issue content before it is processed by the agent.- [SAFE]: The skill operates within the scope of a defined 'project issue contract' and utilizes standard platform tools for user interaction (AskUserQuestion). No patterns of obfuscation, credential theft, or persistence were detected.

new-milestone