systematic-debugging
No security findings. Scanned 1 time, most recently 2026-02-01.
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
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
- Package
- 11 files, 40 KB
- SKILL.md
- 1486 words, 12+ sections
- Code
- TypeScript (1), Shell (1)
SKILL.md covers: Systematic Debugging · Overview · The Iron Law · When to Use · The Four Phases · Phase 1: Root Cause Investigation · Phase 2: Pattern Analysis · Phase 3: Hypothesis and Testing · Phase 4: Implementation · Red Flags - STOP and Follow Process · your human partner's Signals You're Doing It Wrong · Common Rationalizations
Findings
No findings. SAFE
What is in the package
| File | Kind | Size |
|---|---|---|
CREATION-LOG.md | doc | 4.2 KB |
SKILL.md | doc | 9.7 KB |
condition-based-waiting-example.ts | script | 4.9 KB |
condition-based-waiting.md | doc | 3.4 KB |
defense-in-depth.md | doc | 3.6 KB |
find-polluter.sh | script | 1.5 KB |
root-cause-tracing.md | doc | 5.2 KB |
test-academic.md | doc | 653 B |
test-pressure-1.md | doc | 1.9 KB |
test-pressure-2.md | doc | 2.2 KB |
test-pressure-3.md | doc | 2.6 KB |
Package contents recorded 2026-10-22 at commit 06b92f36820f. 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://github.com/obra/superpowers
- Raw scan result: systematic-debugging-scan.json
- Badge for your README:
- Request a re-scan