sync-agent-rules
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The script
scripts/sync_agent_rules.pyexecutes shell commands by invoking the systemgitbinary viasubprocess.runto perform repository actions such as clone, fetch, pull, and push. - [INDIRECT_PROMPT_INJECTION]: The skill's primary purpose is to fetch instructions from a remote repository and install them in the agent's global configuration files (
~/.claude/CLAUDE.mdand~/AGENTS.md). - Ingestion points: Instructions are retrieved from user-specified Git repositories in
scripts/sync_agent_rules.py. - Boundary markers: None; the skill does not wrap external content in delimiters or provide warnings to ignore embedded instructions.
- Capability inventory: The skill has the capability to write to the user's home directory and execute shell commands via
git. - Sanitization: No validation or sanitization is performed on the markdown content fetched from the remote repository before it is applied to the system.
- [EXTERNAL_DOWNLOADS]: The skill performs network operations to download content from external Git repositories provided by the user during the initialization phase.
Audit Metadata