glm-coding-agent
Verdict safe, but 1 finding (1 medium), mainly data exfiltration. Most recent scan 2026-02-06.
The glm-coding-agent skill is a wrapper for the Claude Code CLI that integrates with GLM 4.7 via Z.AI's API. The skill implements a git-based safety workflow for code changes. Security analysis reveals MEDIUM severity concerns around credential handling (reading API keys from config files and exposing via environment variables) and LOW severity issues with missing optional metadata and external binary dependencies. The skill does not contain prompt injection, data exfiltration to external servers, or malicious code execution. The primary security concern is credential exposure risk, which can be mitigated through proper file permissions and secure credential storage practices. The skill's behavior matches its description and does not exhibit deceptive characteristics.
Scanner's overall assessment (LLM analyzer)
Second scanner: NVIDIA SkillSpector
The two scanners disagree: Cisco found nothing and SkillSpector says do not install. One of them has a blind spot here; read the skill before trusting either. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Run Claude Code CLI with GLM 4.7 (via Z.AI) with automatic git safety net - checkpoint, experiment branch, review workflow. Cheap 200k context.
- Package
- 2 files, 16 KB
- SKILL.md
- 2112 words, 12+ sections
- Code
- None. Instructions only.
- Requires
- bins:
claude
SKILL.md covers: GLM Coding Agent · Quick Start · From Command Line · From OpenClaw (all platforms) · macOS/Linux · Windows · After completion → interactive review: · 1️⃣ ACCEPT - Merge to main · 2️⃣ REVIEW - Selective staging · 3️⃣ REJECT - Discard all · 4️⃣ KEEP - Manual fixes · Background mode
Findings
MEDIUM Credential Exposure via OpenClaw Config File Access Data Exfiltrationllm
The skill reads API keys from the OpenClaw configuration file (~/.openclaw/openclaw.json on Unix, %USERPROFILE%\.openclaw\openclaw.json on Windows) and exports them as environment variables (ANTHROPIC_AUTH_TOKEN). While reading from a local config file is a common pattern, this creates a potential credential exposure risk if the skill is used in an untrusted context or if the config file permissions are misconfigured. The API key is then passed to the claude CLI tool via environment variable, which could be logged or exposed through process listings.
SKILL.md
API_KEY=$(jq -r '.models.providers.zai.apiKey // empty' "$CONFIG_FILE" 2>/dev/null)
export ANTHROPIC_AUTH_TOKEN="$API_KEY"What is in the package
| File | Kind | Size |
|---|---|---|
README.md | doc | 994 B |
SKILL.md | doc | 16 KB |
External hosts referenced
api.z.ai raw.githubusercontent.com
Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.
Environment variables referenced
CONFIG_FILE API_KEY PROFILE
Package contents recorded 2026-10-22. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.
What we checked
- Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
- Behavioral analyzer. Checks what the skill asks the agent to do against what its description claims it does.
- Llm analyzer. A language model reads the skill and reports intent-level issues the rules cannot express.
- Trigger analyzer. Looks for instructions that fire on conditions the user did not ask for.
- Meta analyzer. A second model pass that validates, deduplicates and re-scores the other analyzers' findings.
What we did not check
- Runtime behaviour. The skill was not executed; findings come from reading its files.
- Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
- Content the analyzers cannot read: images, binaries, and some non-English text.
- Known scanner bypass classes. See the methodology and limitations page.
Sources
- Repository: https://clawhub.ai/skills/glm-coding-agent
- Raw scan result: glm-coding-agent-scan.json
- Badge for your README:
- Request a re-scan