The Agent Skills Directory

[COMMAND_EXECUTION]: The skill makes extensive use of the Bash tool to execute shell commands for repository management and software builds.
Evidence: The skill executes gh api commands to manage branches, create pull requests, and update file contents. It also runs npm install and npm test within user workspaces to validate changes.
[DATA_EXFILTRATION]: The skill is designed to read file contents from the local environment and transmit them to external GitHub repositories.
Evidence: It uses mcp__github__push_files and Bash (via gh api) to upload data from files like package.json and CLAUDE.md to remote servers controlled by GitHub.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external source files which could contain malicious instructions designed to influence the agent's behavior during the synchronization process.
Ingestion points: Reads project files from workspaces using the Read tool and fetches remote content using GitHub API calls within Bash commands.
Boundary markers: Absent; there are no delimiters or instructions to the agent to ignore potentially malicious content within the processed files.
Capability inventory: The skill possesses high-impact capabilities including arbitrary shell execution (Bash), file system modification (Write, Edit), and remote data transmission (mcp__github__push_files).
Sanitization: Absent; the skill does not implement validation or escaping for the content it reads and subsequently uses in further operations.

agent-sync-coordinator