skill-creator

Warn

Audited by Runlayer on Mar 10, 2026

Risk Level: MEDIUM
Scan Summary
Max Score
88%
Files
21
Flagged
8
Chunks
43
Flagged Files (8)
skill-creator/scripts/run_loop.pyMEDIUM
87.9%

Tool passed security scan

Risky tool definition detected

Description: != "none": if args.report == "auto": timestamp = time.strftime("%Y%m%d_%H%M%S") live_report_path = Path(tempfile.gettempdir()) / f"skill_description_report_{skill_path.name}_{timestamp}.html" else: live_report_path = Path(args.report) # Open the report immediately so the user can watch live_report_path.write_text("<html><body><h1>Starting optimization loop...</h1><meta http-equiv='refresh' content='5'></body></html>") webbrowser.open(str(live_report_path)) else: live_report_path = N

skill-creator/SKILL.mdMEDIUM
87.1%

Tool passed security scan

Risky tool definition detected

``` For iteration 2+, also pass `--previous-workspace <workspace>/iteration-<N-1>`. **Cowork / headless environments:** If `webbrowser.open()` is not available or the environment has no display, use `--static <output_path>` to write a standalone HTML file instead of starting a server. Feedback will be downloaded as a `feedback.json` file when the user clicks "Submit All Reviews". After download, copy `feedback.json` into the workspace directory for the next iteration to pick up.

If you're in Cowork, please specifically put "Create evals JSON and run `eval-viewer/generate_review.py` so human can review test cases" in your TodoList to make sure it happens.

skill-creator/eval-viewer/generate_review.pyMEDIUM
84.2%

Risky tool definition detected

Tool: skill-creator/eval-viewer/generate_review.py [2/2] Description: None: if self.path == "/" or self.path == "/index.html": # Regenerate HTML on each request (re-scans workspace for new outputs) runs = find_runs(self.workspace) benchmark = None if self.benchmark_path and self.benchmark_path.exists(): try: benchmark = json.loads(self.benchmark_path.read_text()) except (json.JSONDecodeError, OSError): pass html = generate_html(runs, self.skill_name, self.previous, benchmark) content = html.enco

skill-creator/scripts/generate_report.pyLOW
72.0%

Tool passed security scan

Risky tool definition detected

') # Add result for each test query (with different background) for qinfo in test_queries: r = test_by_query.get(qinfo["query"], {}) did_pass = r.get("pass", False) triggers = r.get("triggers", 0) runs = r.get("runs", 0) icon = "✓" if did_pass else "✗" css_class = "pass" if did_pass else "fail" html_parts.append(f' <td class="result test-result {css_class}">{icon}<span class="rate">{triggers}/{runs}</span></td> ') html_parts.append(" </tr> ") html_parts.append(""" </tbody> </table> </div> """) h

skill-creator/scripts/improve_description.pyLOW
63.2%

Tool passed security scan

skill-creator/scripts/security_scan.pyLOW
63.1%

Tool passed security scan

skill-creator/eval-viewer/viewer.htmlLOW
60.3%

Tool passed security scan

skill-creator/scripts/aggregate_benchmark.pyLOW
55.6%

Tool passed security scan

Passed Files (13)Click to expand
skill-creator/.gitignoreOK
46.2%

Tool passed security scan

skill-creator/scripts/run_eval.pyOK
42.6%

Tool passed security scan

skill-creator/LICENSE.txtOK
37.4%

Tool passed security scan

skill-creator/agents/grader.mdOK
23.5%

Tool passed security scan

skill-creator/assets/eval_review.htmlOK
22.2%

Tool passed security scan

skill-creator/references/sanitization_checklist.mdOK
21.7%

Tool passed security scan

skill-creator/agents/analyzer.mdOK
21.0%

Tool passed security scan

skill-creator/scripts/init_skill.pyOK
10.0%

Tool passed security scan

skill-creator/scripts/package_skill.pyOK
10.0%

Tool passed security scan

skill-creator/references/schemas.mdOK
9.9%

Tool passed security scan

skill-creator/scripts/quick_validate.pyOK
6.4%

Tool passed security scan

skill-creator/scripts/utils.pyOK
6.4%

Tool passed security scan

skill-creator/agents/comparator.mdOK
5.2%

Tool passed security scan

Audit Metadata
Max File Score
88%
Classification
KNOWN_SERVER_ALL_UNKNOWN
Files Scanned
21
Files Flagged
8
Chunks Analyzed
43
Analyzed
Mar 10, 2026, 06:19 AM
Security Audit — runlayer — skill-creator