SKILLEMALL.ai
GitHub ↗ RU Sign in

CB codeql-local-triage

Answers "why did CodeQL flag this, and which line must change for it to stop" — reproducible causal triage of ONE specific alert via variant bisection. Triggers on "确认 taint 源 / 复现这个 CodeQL 告警 / 为什么 CodeQL 报这个 / CodeQL 误报 / 这个告警是不是误报 / 本地跑 CodeQL / 验证安全告警是否修好 / confirm the taint source / why does CodeQL flag this / is this alert a false positive / reproduce this CodeQL alert / verify a security-alert fix", or when handed a .sarif file and asked where the taint starts. NOT for whole-repo alert audits or bulk dismissal — it never closes alerts for you and never replaces the Code Scanning suite. NOT for Java/JS/Go (Python only today). The prefilter lists candidate sensitive NAMES in files/dirs you point at; it draws no conclusion and produces no audit report. Keywords — CodeQL, Code Scanning, taint source, data flow, SARIF, codeFlows, false positive, py/clear-text-storage-sensitive-data, CWE-312.

ClawHub Claude Code author: Elisabeth15501 v1.0.8 MIT-0 17 files · 7 scripts body ≈ 3 566 tokens Open the sourceclawhub.ai↗ analyzed 7 d ago

Answers "why did CodeQL flag this, and which line must change for it to stop" — reproducible causal triage of ONE specific alert via variant bisection.

As a process B 74/100 · Nearly there — weak spots: result and completion, inputs and preconditions, progress reporting

AnalyzerGitHubAI and agentsData and analyticstype 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
89/100
safety, quality, tests
Safety 60%
95
Quality 40%
79
Run on models
none yet
Process rating
B
74/100
Nearly there
Inputs and preconditions w 11
0
Progress reporting w 2
0
Result and completion w 14
40
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.

Broad scope 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 asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

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 · 1

    ✓ No critical or high findings

    Medium and low: 1
    • medium Broad scope meta-broad-allowed-tools SKILL.md:1
      Broad tool permissions pre-approved: Bash
      allowed-tools: Read Grep Glob Bash

    Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "slug"
    • note frontmatter-key unknown frontmatter key "displayName"
    • note frontmatter-key unknown frontmatter key "summary"
    • note frontmatter-key unknown frontmatter key "homepage"
    • note frontmatter-key unknown frontmatter key "agent_created"
    • note frontmatter-key unknown frontmatter key "permissions"

    Process rating: all ten parameters 74/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 40Result and completion. Does not say what the result is
    • 50Failures and branches. 0 branches, has a failure section
    • 100Tools and files. Tools declared in frontmatter
    • 100Steps. 33 steps
    • 100When it triggers. States when to use and when not to
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3566 tokens
    • 100Running it twice. Mutating operations check current state
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low The response is described with custom markup (5 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
    • +3Description length 906: 120–800 characters recommended
    • +3Output format is not stated: the model decides each time
    • +4No input/output examples
    • -31 of 4 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +4Description says when NOT to use the skill
    • +4Structure: 16 headings
    • +3Step-by-step instructions: 33 items
    • +4Reference files are cited in the instructions (5 of 5)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.

    External checks

    ClawHub: clean
    This skill is a disclosed local CodeQL triage helper that reads specified source/SARIF files, writes temporary variant copies, and optionally runs a local CodeQL binary without hidden network, persistence, or alert-management behavior.
    LLM: benign (high) · VirusTotal: · 9 Oct 2026