refactor(entropy): B5 — two-stage context-classified suppression pipeline
The v7.0.0 entropy-scanner ran rules 11-13 (GLSL/CSS-in-JS/inline-markup
line-proximity suppressions) for every line regardless of file type. A
polyglot `.ts` file with an embedded fragment-shader template literal
could therefore mask a real high-entropy credential when the credential
literal happened to share a line with a GLSL keyword. Critical-review
B5 documented the false-negative class.
Refactor:
* New `classifyFileContext(absPath, lines)` returns
`'shader-dominant' | 'markup-dominant' | 'code-dominant' | 'mixed'`,
keyed off file extension with a content-density fallback for
code-extension files (≥50% of sampled non-blank lines matching
GLSL/inline-markup → downgrade to `mixed`).
* `isFalsePositive(str, line, absPath, context)` gates rules 11-13
on `context !== 'code-dominant'`. Rules 1-10 and 14-19 still run
unconditionally, so URL/path/test-fixture/ffmpeg/UA/SQL/error-
template suppression behaves identically.
* `scanFileContent` computes `fileContext` once per file and threads
it through every per-string suppression check.
Conservative defaults to keep the regression surface minimal:
* Files with `<5` sampled non-blank lines fall back to `mixed`
(preserves the existing rule-11/12/13 behaviour for the single-
line .js fixtures used by entropy-context.test.mjs).
* Unknown extensions fall back to `mixed`.
* Code-extension files densely populated with shader/markup
content fall back to `mixed`.
Net effect: a `.ts` file with an embedded GLSL block but mostly TS
code on the surrounding lines now surfaces credentials that the
v7.0.0 line-proximity heuristic suppressed. Pure shader/markup
files are unaffected (extension skip / mixed default).
New fixture: tests/fixtures/entropy/polyglot-ts-with-glsl.ts (with
runtime placeholder so it does not commit a high-entropy literal).
+3 tests in tests/scanners/entropy-context.test.mjs (26 → 29).
Existing entropy.test.mjs and entropy-context.test.mjs all remain
green. Full suite 1658 → 1661.
Refs: Batch B Wave 5 / Step 12 / v7.2.0
critical-review-2026-04-20.md §B5
This commit is contained in:
parent
d441abba20
commit
04f1593df3
3 changed files with 197 additions and 8 deletions
32
plugins/llm-security/tests/fixtures/entropy/polyglot-ts-with-glsl.ts
vendored
Normal file
32
plugins/llm-security/tests/fixtures/entropy/polyglot-ts-with-glsl.ts
vendored
Normal file
|
|
@ -0,0 +1,32 @@
|
|||
// Polyglot TypeScript fixture for the entropy-scanner B5 regression.
|
||||
//
|
||||
// Pre-B5 behaviour: rule 11 (GLSL_KEYWORDS line-proximity) suppressed any
|
||||
// high-entropy string that happened to share a line with shader keywords.
|
||||
// In a `.ts` file with an embedded fragment-shader template literal, a real
|
||||
// credential on the closing brace line would be silently dismissed.
|
||||
//
|
||||
// Post-B5 behaviour: classifyFileContext returns 'code-dominant' for `.ts`
|
||||
// files (unless the file is overwhelmingly shader/markup), which disables
|
||||
// rules 11-13. The credential below is therefore detected.
|
||||
//
|
||||
// The placeholder __ENTROPY_PAYLOAD_PLACEHOLDER__ is replaced at test time
|
||||
// with a randomly generated high-entropy string. The static fixture stays
|
||||
// out of the pre-edit-secrets hook because no real high-entropy literal is
|
||||
// committed to disk.
|
||||
|
||||
const fragmentShader = `
|
||||
precision highp float;
|
||||
uniform vec3 u_resolution;
|
||||
uniform float u_time;
|
||||
varying vec2 v_uv;
|
||||
void main() {
|
||||
vec3 color = vec3(v_uv, sin(u_time));
|
||||
gl_FragColor = vec4(color, 1.0);
|
||||
}
|
||||
`;
|
||||
|
||||
// The next line ends a uniform vec3 declaration AND carries the placeholder
|
||||
// — exactly the kind of GLSL-adjacent line that rule 11 used to suppress.
|
||||
const placeholder = "__ENTROPY_PAYLOAD_PLACEHOLDER__"; // uniform vec3 normal;
|
||||
|
||||
export { fragmentShader, placeholder };
|
||||
|
|
@ -262,4 +262,82 @@ describe('entropy-scanner context suppression (v7.0.0+)', () => {
|
|||
await rm(fx, { recursive: true, force: true });
|
||||
});
|
||||
});
|
||||
|
||||
describe('D. B5 file-context classification (v7.2.0)', () => {
|
||||
it('B5 regression: code-dominant .ts file with embedded GLSL — credential adjacent to shader is detected', async () => {
|
||||
// Polyglot TS file: many code lines, a few GLSL lines inside a template
|
||||
// literal, and a credential-shaped string on a line that happens to
|
||||
// contain GLSL keyword tokens. Pre-B5 rule 11 line-proximity suppressed
|
||||
// this. Post-B5 classifyFileContext returns 'code-dominant' (sample is
|
||||
// mostly TS code, <50% GLSL/markup), rules 11-13 are gated off, and
|
||||
// the credential is detected.
|
||||
const fx = await newRoot('ent-b5-polyglot-');
|
||||
const fixtureContent = [
|
||||
'import { Renderer } from "./renderer";',
|
||||
'',
|
||||
'const fragmentShader = `',
|
||||
' precision highp float;',
|
||||
' uniform vec3 u_resolution;',
|
||||
' varying vec2 v_uv;',
|
||||
'`;',
|
||||
'',
|
||||
'// Adjacent line carries GLSL tokens AND the credential payload.',
|
||||
'const blob = "' + PAYLOAD + '"; // uniform vec3 normal;',
|
||||
'',
|
||||
'export { fragmentShader, blob };',
|
||||
].join('\n');
|
||||
await writeFixture(fx, 'shader-app.ts', fixtureContent);
|
||||
resetCounter();
|
||||
const discovery = await discoverFiles(fx);
|
||||
const result = await scan(fx, discovery);
|
||||
assert.ok(
|
||||
result.findings.length >= 1,
|
||||
'expected B5 to surface credential in code-dominant .ts despite GLSL neighbour; got ' + result.findings.length
|
||||
);
|
||||
await rm(fx, { recursive: true, force: true });
|
||||
});
|
||||
|
||||
it('B5 control: legitimate .glsl file with high-entropy hash in shader source is still suppressed (extension skip)', async () => {
|
||||
// A pure-shader file is skipped at the file-extension gate, never
|
||||
// reaching classifyFileContext. This control confirms the extension
|
||||
// skip still works (B5 only changed line-level rule gating).
|
||||
const fx = await newRoot('ent-b5-glsl-');
|
||||
await writeFixture(fx, 'noise.glsl',
|
||||
'uniform vec3 u_seed;\nvec3 rand = vec3(' + PAYLOAD + ');\n');
|
||||
resetCounter();
|
||||
const discovery = await discoverFiles(fx);
|
||||
const result = await scan(fx, discovery);
|
||||
assert.equal(result.findings.length, 0, '.glsl files remain extension-skipped');
|
||||
await rm(fx, { recursive: true, force: true });
|
||||
});
|
||||
|
||||
it('B5 control: shader-dominant .ts file with ≥50% GLSL lines downgrades to mixed and suppresses', async () => {
|
||||
// A code-extension file that is *mostly* shader template content —
|
||||
// rule 11 should still fire because classifyFileContext downgrades it
|
||||
// to 'mixed' (≥50% sampled lines match GLSL/INLINE_MARKUP).
|
||||
const fx = await newRoot('ent-b5-shader-ts-');
|
||||
const fixtureContent = [
|
||||
'uniform vec3 u_resolution;',
|
||||
'uniform vec3 u_camera_pos;',
|
||||
'uniform float u_time;',
|
||||
'varying vec2 v_uv;',
|
||||
'varying vec3 v_normal;',
|
||||
'attribute vec3 position;',
|
||||
'attribute vec2 uv;',
|
||||
'precision highp float;',
|
||||
'gl_Position = vec4(position, 1.0);',
|
||||
'gl_FragColor = vec4(1.0);',
|
||||
'const blob = "' + PAYLOAD + '"; // uniform vec3 normal;',
|
||||
].join('\n');
|
||||
await writeFixture(fx, 'shader-heavy.ts', fixtureContent);
|
||||
resetCounter();
|
||||
const discovery = await discoverFiles(fx);
|
||||
const result = await scan(fx, discovery);
|
||||
assert.equal(
|
||||
result.findings.length, 0,
|
||||
'expected shader-dense .ts (≥50% GLSL lines) to downgrade to mixed and suppress; got ' + result.findings.length
|
||||
);
|
||||
await rm(fx, { recursive: true, force: true });
|
||||
});
|
||||
});
|
||||
});
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue