SKILLEMALL.ai
RU Sign in

BC canonry

Navigate Canonry through connected MCP tools or the `cnry` CLI to inspect evidence, diagnose changes, plan measurement, review integrations, and report results. Use this optional host-native skill for CLI workflows and detailed references; connected MCP users can operate through canonry_help without installing a local runtime or skill.

ClawHub Agent Skills author: Arber X v5.0.1+92ebeea MIT-0 9 files body ≈ 3 491 tokens Open the sourceclawhub.ai↗ analyzed 8 h ago

Navigate Canonry through connected MCP tools or the cnry CLI to inspect evidence, diagnose changes, plan measurement, review integrations, and report results.

As a process C 58/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice

IntegrationAI 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
B
86/100
safety, quality, tests
Safety 60%
88
Quality 40%
84
Run on models
none yet
Process rating
C
58/100
Has gaps
Result and completion w 14
0
When it triggers w 12
20
Running it twice w 4
30
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration 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 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.

How to improve

    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 · 4

    ✓ No critical or high findings

    Medium and low: 4
    • medium Exfiltration net-credential-use references/server-side-traffic.md:430
      Credential used in a network call (verify the destination is the intended service)
      curl -s -X POST -H "Authorization: Bearer $CF_TOKEN" -H "Content-Type: application/json" \
    • medium Exfiltration net-credential-use references/server-side-traffic.md:451
      Credential used in a network call (verify the destination is the intended service)
      curl -s -H "Authorization: Bearer $CF_TOKEN" \
    • low Exfiltration exfil-secret-in-url references/google-business-profile.md:86
      Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (destination is a well-known publishing service; security demo / example; quoted — discussed, not commanded)
      **Account-credential gotcha:** API calls use your **Application Default Credentials** (`gcloud auth application-default login` → `print-access-token`), while `gcloud services enable` uses the separate
      known servicedemoquoted
    • low Exfiltration net-credential-use references/google-business-profile.md:86
      Credential used in a network call (verify the destination is the intended service) (destination is a well-known publishing service; security demo / example; quoted — discussed, not commanded)
      **Account-credential gotcha:** API calls use your **Application Default Credentials** (`gcloud auth application-default login` → `print-access-token`), while `gcloud services enable` uses the separate
      known servicedemoquoted

    Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note edit-residue the text marks something as outdated (lines 179): check that old rules are not kept next to new ones — the full check reads the text for contradictions

    Process rating: all ten parameters 58/100

    • 0Result and completion. Does not say what the result is
    • 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 (web) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 12 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3491 tokens
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

    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
    • +4No input/output examples
    • +1No license
    • +2Single-language instructions
    • +3Description length 337: enough signal without eating the budget
    • +4Structure: 9 headings
    • +3Step-by-step instructions: 12 items
    • +4Reference files are cited in the instructions (7 of 7)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.

    External checks

    ClawHub: suspicious
    Canonry is a coherent operations skill, but its reference docs include high-impact integration and credential-handling workflows that need review before installation.
    LLM: suspicious (high) · 12 Sept 2026