You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+13-13Lines changed: 13 additions & 13 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -37,7 +37,7 @@ Skill Scanner is a detection tool. It identifies known and probable risk pattern
37
37
38
38
-**No findings ≠ no risk.** A scan that returns "No findings" indicates that no known threat patterns were detected. It does not guarantee that a skill is secure, benign, or free of vulnerabilities.
39
39
-**Coverage is inherently incomplete.** The scanner combines signature-based detection, LLM-based semantic analysis, behavioral dataflow analysis, optional cloud services, and configurable rule packs. While this approach improve coverage, no automated tool can detect every technique, especially novel or zero-day attacks.
40
-
-**False positives and false negatives can occur.** Consensus modes and meta-analysis reduce noise, but no configuration eliminates all incorrect classifications. Tune the [scan policy](docs/scan-policy.md) to your risk tolerance.
40
+
-**False positives and false negatives can occur.** Consensus modes and meta-analysis reduce noise, but no configuration eliminates all incorrect classifications. Tune the [scan policy](docs/user-guide/custom-policy-configuration.md) to your risk tolerance.
41
41
-**Human review remains essential.** Automated scanning is one component of a defense-in-depth strategy. High-risk or production deployments should pair scanner results with manual code review and/or threat modeling.
42
42
43
43
---
@@ -46,18 +46,18 @@ Skill Scanner is a detection tool. It identifies known and probable risk pattern
46
46
47
47
| Guide | Description |
48
48
|-------|-------------|
49
-
|[Quick Start](docs/quickstart.md)| Get started in 5 minutes |
50
-
|[Architecture](docs/architecture.md)| System design and components |
51
-
|[Threat Taxonomy](docs/threat-taxonomy.md)| Complete AITech threat taxonomy with examples |
52
-
|[LLM Analyzer](docs/llm-analyzer.md)| LLM configuration and usage |
53
-
|[Meta-Analyzer](docs/meta-analyzer.md)| False positive filtering and prioritization |
**LLM provider note:**`--llm-provider` currently accepts `anthropic` or `openai`.
183
-
For Bedrock, Vertex, Azure, Gemini, and other LiteLLM backends, set provider-specific model strings and environment variables (see `docs/llm-analyzer.md`).
183
+
For Bedrock, Vertex, Azure, Gemini, and other LiteLLM backends, set provider-specific model strings and environment variables (see [LLM Analyzer docs](docs/architecture/analyzers/llm-analyzer.md)).
0 commit comments