coding-agent
No security findings. Scanned 2 times, most recently 2026-02-06.
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 Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
- Package
- 4 files, 21 KB
- SKILL.md
- 1832 words, 12+ sections
- Code
- None. Instructions only.
- Requires
- anyBins:
claudecodexopencodepi
SKILL.md covers: Coding Agent (bash-first) · ⚠️ PTY Mode Required! · ✅ Correct - with PTY · ❌ Wrong - no PTY, agent may break · Bash Tool Parameters · Process Tool Actions (for background sessions) · Quick Start: One-Shot Tasks · Quick chat (Codex needs a git repo!) · Or in a real project - with PTY! · The Pattern: workdir + background + pty · Start agent in target directory (with PTY!) · Returns sessionId for tracking
Findings
No findings. SAFE
What is in the package
| File | Kind | Size |
|---|---|---|
README.md | doc | 1.9 KB |
SKILL.md | doc | 12 KB |
references/claude-code.md | doc | 3.9 KB |
references/gemini-cli.md | doc | 3.4 KB |
External hosts referenced
github.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
REVIEW_DIR
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.
Scan history
| Date | Verdict | Findings | Change | Analyzers | Raw |
|---|---|---|---|---|---|
| SAFE | 0 | -6 | static behavioral llm trigger meta | JSON | |
| CRITICAL | 6 | first scan | static behavioral llm trigger meta | JSON |
Sources
- Repository: https://clawhub.ai/skills/multi-coding-agent
- Raw scan result: multi-coding-agent-scan.json
- Badge for your README:
- Request a re-scan