ClawAudit verdict

gstack-orchestrate

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Accesses agent memory AND writes files

Orchestrates parallel Claude Code subagents in git worktrees to execute implementation plans; the broad tool access (Bash, Write, Agent) is consistent with a legitimate orchestration skill for software development.

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

53
security
60
transparency
90
maintenance

What it does

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

Capability combination high

Accesses agent memory AND writes files — may modify agent behavior persistently

LLM01 · LLM06 · ASI01 · ASI06

Permission integrity

Performs file operations but does not declare file-accessing binaries

file_read+write

Installs packages at runtime — transitive dependencies are not auditable

package_install

Accesses agent memory/configuration files

agent_memory

Findings (1)

Pattern match medium

References agent configuration files

SKILL.md · code · CLAUDE.md

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B/F). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

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