gastown
Multi-agent orchestrator for Claude Code. Use when user mentions gastown, gas town, gt commands, bd commands, convoys, polecats, crew, rigs, slinging work, multi-agent coordination, beads, hooks, molecules, workflows, the witness, the mayor, the refinery, the deacon, dogs, escalation, or wants to run multiple AI agents on projects simultaneously. Handles installation, workspace setup, work tracking, agent lifecycle, crash recovery, and all gt/bd CLI operations.
93
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Security
3 findings — 3 medium severity. This skill can be installed but you should review these findings before use.
W011: Third-party content exposure detected (indirect prompt injection risk)
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
Third-party content exposure detected (high risk: 0.80). Yes — the skill explicitly instructs the agent to fetch and read arbitrary public GitHub repositories and files (e.g., "gt rig add ... https://github.com/you/repo.git" and "Use WebFetch to read specific files from the repo" in SKILL.md and references/setup.md), so untrusted, user‑generated third‑party content is ingested and can influence subsequent commands and actions.
W012: Unverifiable external dependency detected (runtime URL that controls agent)
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
Potentially malicious external URL detected (high risk: 0.90). The skill instructs runtime fetching/execution of remote code (e.g., "go install github.com/steveyegge/gastown/cmd/gt@latest" and "go install github.com/steveyegge/beads/cmd/bd@latest") and explicitly points to https://github.com/steveyegge/gastown for WebFetch/reading reference files, so external GitHub content would be fetched and can directly control prompts or execute code at runtime.
W013: Attempt to modify system services in skill instructions
What this means
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
Why it was flagged
Attempt to modify system services in skill instructions detected (high risk: 0.75). The skill explicitly instructs the agent to act as the system's operator and execute arbitrary shell commands (install software, run gt/ bd commands, run "gt doctor --fix", start/stop services, create workspaces, etc.), which gives the agent broad ability to modify the machine's state and perform system-level changes even though it doesn't explicitly demand sudo or user creation — this delegation of terminal control is a high-risk pattern.
- Repository
- numman-ali/n-skills
- Commit
8de01ac
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.