audit-context-building
No security findings. Scanned 1 time, most recently 2026-02-06.
Second scanner: NVIDIA SkillSpector
Independent static run, no language model, over the same files as the Cisco scan above. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Enables ultra-granular, line-by-line code analysis to build deep architectural context before vulnerability or bug finding.
- Package
- 4 files, 31 KB
- SKILL.md
- 1292 words, 12+ sections
- Code
- None. Instructions only.
SKILL.md covers: Deep Context Builder Skill (Ultra-Granular Pure Context Mode) · 1. Purpose · 2. When to Use This Skill · 3. How This Skill Behaves · Rationalizations (Do Not Skip) · 4. Phase 1 — Initial Orientation (Bottom-Up Scan) · 5. Phase 2 — Ultra-Granular Function Analysis (Default Mode) · 5.1 Per-Function Microstructure Checklist · 5.2 Cross-Function & External Flow Analysis · 5.3 Complete Analysis Example · 5.4 Output Requirements · 5.5 Completeness Checklist
Findings
No findings. SAFE
What is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 9.3 KB |
resources/COMPLETENESS_CHECKLIST.md | doc | 1.8 KB |
resources/FUNCTION_MICRO_ANALYSIS_EXAMPLE.md | doc | 18 KB |
resources/OUTPUT_REQUIREMENTS.md | doc | 2.4 KB |
Package contents recorded 2026-10-22 at commit a50696e20581. 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/trailofbits/skills
- Raw scan result: plugins-audit-context-building-skills-audit-context-building-scan.json
- Badge for your README:
- Request a re-scan