Caveat verdict

flow-swarm

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Receives external input AND executes processes

Multi-agent swarm orchestration skill for Claude Code using documented MCP tooling; all capabilities (package install, file read, process exec) are clearly for coordinating local agent workflows and are fully transparent.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

10
security
70
transparency
90
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination critical

Receives external input AND executes processes — the shape of a command & control channel

LLM05 · LLM06 · ASI10

Capability combination high

Installs packages AND executes processes — opaque dependency chain with execution

LLM03 · ASI04

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (1)

Pattern match high

Uses exec() — may execute shell commands

SKILL.md · code · exec (

Permissions & capabilities

No declared permissions — minimal attack surface.

network_inpackage_installfile_readprocess_exec
Check another skill Browse the registry Auditing your own skills or configs? Use the API