SKILLEMALL.ai
GitHub ↗ RU Sign in

CC buzz-acp

Deploy and manage AI agents (OpenClaw, Claude Code) as first-class participants in a self-hosted Buzz workspace via ACP.

Not recommendedcritical or high security findings
ClawHub Agent Skills author: Darren Robinson v0.2.1 MIT-0 18 files body ≈ 2 383 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

Deploy and manage AI agents (OpenClaw, Claude Code) as first-class participants in a self-hosted Buzz workspace via ACP.

As a process C 56/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice

ProcedureDockerGitHubPostgreSQLAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
C
66/100
safety, quality, tests
Safety 60%
60
Quality 40%
74
Run on models
none yet
Process rating
C
56/100
Has gaps
Result and completion w 14
0
Progress reporting w 2
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 15

  • high Dangerous commands cmd-pipe-to-shell README.md:136
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --default-toolchain stable
Medium and low: 14
  • medium Dangerous commands cmd-privilege SKILL.md:91
    Privilege escalation / world-writable permissions
    sudo cp systemd/buzz-relay.service /etc/systemd/system/
  • medium Dangerous commands cmd-privilege SKILL.md:119
    Privilege escalation / world-writable permissions
    sudo cp systemd/buzz-marvin.service /etc/systemd/system/
  • low Exfiltration read-dotenv docs/troubleshooting.md:47
    Reads a .env file
    source /path/to/buzz/.env
  • low Secrets in code secret-high-entropy-token examples/ccagent/package-lock.json:66
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    "integrity": "sha5…aip+DL8W…kw8+SAC/6hD2PA==",
    fixturequoted
  • low Secrets in code secret-high-entropy-token examples/ccagent/package-lock.json:105
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    "integrity": "sha5…kT6+8Wk/gVu8…nZn+f0TZhgYP+82PS…1kn+w==",
    fixturequoted
  • low Secrets in code secret-high-entropy-token examples/ccagent/package-lock.json:238
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition; test fixture / example file)
    "integrity": "sha5…S4F+im88…HRE/cYlx…2oE/ufM0p61IKng==",
    detectorfixture
  • low Secrets in code secret-high-entropy-token examples/ccagent/package-lock.json:289
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition; test fixture / example file)
    "integrity": "sha5…rdY+ziCYCPMmtZjjIwOmXFjmyzEHn+UUxk5of+SYsj…5hY/rOAw==",
    detectorfixture
  • low Secrets in code secret-high-entropy-token examples/ccagent/package-lock.json:374
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition; test fixture / example file)
    "integrity": "sha5…NmN+loZK…eAz+famM…vZz+zT1jlh/keC3Rj/lg==",
    detectorfixture
  • low Exfiltration read-dotenv README.md:153
    Reads a .env file
    cp .env.example .env
  • low Exfiltration read-dotenv README.md:183
    Reads a .env file
    source .env
  • low Exfiltration read-dotenv SKILL.md:74
    Reads a .env file
    cp .env.example .env   # edit passwords for production
  • low Dangerous commands cmd-background-process SKILL.md:92
    Starts a background / autostarted process
    sudo systemctl daemon-reload && sudo systemctl enable --now buzz-relay
  • low Dangerous commands cmd-background-process SKILL.md:122
    Starts a background / autostarted process
    sudo systemctl enable --now buzz-marvin
  • low Exfiltration read-dotenv SKILL.md:229
    Reads a .env file (detector / deny-list definition)
    `BUZZ_RELAY_PRIVATE_KEY` not being read. Prefer systemd `EnvironmentFile=`, which handles this correctly. If you must run manually, use `set -a; source .env; set +a` rather than `export $(grep ...)` —
    detector

Files scanned: 15. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 56/100

  • 0Result and completion. Does not say what the result is
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 6 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 19 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2383 tokens

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • +2Single-language instructions
  • +3Description length 120: enough signal without eating the budget
  • +4Structure: 19 headings
  • +3Step-by-step instructions: 19 items
  • +4Has examples (13 code blocks)
  • +4Reference files are cited in the instructions (2 of 2)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.

External checks

ClawHub: suspicious
This is a disclosed Buzz agent bridge, but it needs Review because it persistently lets AI agents post into shared channels and logs message content locally without a clear privacy or approval gate.
LLM: suspicious (medium) · 31 Jul 2026