agent-project-board-sync

Warn

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: MEDIUMOBFUSCATIONREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [OBFUSCATION]: The skill uses a consistent character substitution pattern where the '$' symbol replaces forward slashes ('/') and periods ('.') in critical strings. This is observed in:
  • URLs: https:/$api.example.com$github-sync and https:/$github.com/.
  • System paths: >$dev$null (likely /dev/null).
  • Filenames: .github$board-sync.yml and .$swarm-issue.md.
  • [REMOTE_CODE_EXECUTION]: The skill makes extensive use of npx ruv-swarm to download and execute code from the npm registry at runtime. Although the package is associated with the skill's author, this mechanism allows for the execution of remote code that is not pinned to a specific version or hash.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides functionality to import and process data from external sources, specifically GitHub issues and project cards (via gh issue list and gh project item-list). This constitutes an attack surface where maliciously crafted issue content could influence the agent's behavior during synchronization or report generation.
  • [COMMAND_EXECUTION]: The skill relies on the Bash tool to execute a wide variety of system and GitHub CLI commands. This includes complex piping and data processing (e.g., gh project item-list ... | jq -r ... | while read ... do gh issue view ... done), which represents a high level of autonomous system interaction.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 15, 2026, 11:38 AM
Security Audit — agent-trust-hub — agent-project-board-sync