SKILLEMALL.ai
GitHub ↗ RU Sign in

CC composio

Use 1000+ external apps via Composio - either directly through the CLI or by building AI agents and apps with the SDK

Not recommendedcritical or high security findings
ClawHub Agent Skills author: eladrave v1.0.0 MIT-0 34 files body ≈ 486 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process C 51/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency

GeneratorInfrastructureAI 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
72/100
safety, quality, tests
Safety 60%
63
Quality 40%
85
Run on models
none yet
Process rating
C
51/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
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.

Exfiltration
If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

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.
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 · 8

  • high Exfiltration exfil-webhook-url rules/triggers-webhook.md:154
    Webhook / callback URL commonly used for exfiltration (verify the destination)
    # Use https://abc1….io/composio/triggers in dashboard
Medium and low: 7
  • medium Dangerous commands cmd-pipe-to-shell AGENTS.md:49
    Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)
    curl -fsSL https://composio.dev/install | bash
    vendor-host
  • medium Dangerous commands cmd-pipe-to-shell rules/composio-cli.md:18
    Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)
    curl -fsSL https://composio.dev/install | bash
    vendor-host
  • medium Dangerous commands cmd-pipe-to-shell SKILL.md:18
    Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)
    curl -fsSL https://composio.dev/install | bash
    vendor-host
  • low Secrets in code secret-password-literal rules/setup-api-keys.md:66
    Hard-coded password / key literal (may be an example)
    apiKey: 'sk_c…xyz' // ❌ Security risk!
  • low Secrets in code secret-password-literal rules/setup-api-keys.md:70
    Hard-coded password / key literal (may be an example)
    apiKey: 'sk-p…123' // ❌ Will be exposed in version control
  • low Secrets in code secret-password-literal rules/setup-api-keys.md:76
    Hard-coded password / key literal (may be an example)
    composio = Composio(api_key="sk_c…xyz")  # ❌ Security risk!
  • low Secrets in code secret-password-literal rules/setup-api-keys.md:78
    Hard-coded password / key literal (may be an example)
    client = OpenAI(api_key="sk-p…123")  # ❌ Will be exposed in version control

Files scanned: 34. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

✓ No remarks against the Agent Skills spec

Process rating: all ten parameters 51/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 40Consistency. Frontmatter name (composio) differs from the folder (composiocli)
  • 55Failures and branches. 1 branches
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 70When it triggers. States when to use, but not when not to
  • 85Steps. 8 steps, 1 vague phrases
  • 100Execution cost. Instruction body is 486 tokens
  • 100Running it twice. Mutating operations check current state
  • low The response is described with custom markup (3 tags): a typed call is more reliable

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)
  • +3Description length 117: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +4Structure: 4 headings
  • +3Step-by-step instructions: 8 items
  • +4Has examples (3 code blocks)
  • +4Reference files are cited in the instructions (2 of 31)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.

External checks

ClawHub: suspicious
This skill is a legitimate Composio integration guide, but it gives agents broad authority over external accounts with too little consent, approval, and sensitive-data handling guidance.
LLM: suspicious (high) · VirusTotal: · 29 May 2026