diff options
Diffstat (limited to 'docs')
| -rw-r--r-- | docs/COMPARISON.md | 2 | ||||
| -rw-r--r-- | docs/EXAMPLES.md | 2 | ||||
| -rw-r--r-- | docs/FAQ.md | 2 |
3 files changed, 3 insertions, 3 deletions
diff --git a/docs/COMPARISON.md b/docs/COMPARISON.md index 3f8db12..16cd81a 100644 --- a/docs/COMPARISON.md +++ b/docs/COMPARISON.md @@ -134,7 +134,7 @@ If your threat model excludes extensions with broad permissions, neither approac ## Public benchmarks worth knowing (for axis 2 / axis 3 comparison) -Pi-chrome itself ships a benchmark suite ([`../test-suite/`](../test-suite)) of **41 primitive challenges** plus **4 hermetic BrowserGym-style long-horizon tasks** covering trusted input, pointer humanization, keyboard fidelity, drag/drop, Shadow DOM, iframes, file uploads, strict-CSP screenshot fallback, dynamic waits, tab lifecycle, network observability, fingerprint leaks, and agent-safety honeypots. Scoring tracks expected outcomes per challenge instead of raw PASS count, with `core`, `conditional`, and `quality` gate buckets. That's **driver-level** grading. +Pi-chrome itself ships a benchmark suite ([`../test-suite/`](../test-suite)) of **42 primitive challenges** plus **4 hermetic BrowserGym-style long-horizon tasks** covering trusted input, pointer humanization, keyboard fidelity, drag/drop, Shadow DOM, iframes, file uploads, strict-CSP screenshot fallback and CDP eval/snapshot bypass, dynamic waits, tab lifecycle, network observability, fingerprint leaks, and agent-safety honeypots. Scoring tracks expected outcomes per challenge instead of raw PASS count, with `core`, `conditional`, and `quality` gate buckets. That's **driver-level** grading. For **agent-level** comparison (axis 2), the public benchmarks worth citing: diff --git a/docs/EXAMPLES.md b/docs/EXAMPLES.md index bf3aa0a..434d0f8 100644 --- a/docs/EXAMPLES.md +++ b/docs/EXAMPLES.md @@ -161,6 +161,6 @@ Interactive tools use Chrome's real input layer by default: clicks, typing, fill - fullscreen and other user-activation checks - pages where DOM injection/evaluate is limited, if the agent can use screenshots + coordinates -Strict CSP note: `chrome_snapshot`/`chrome_evaluate` may be blocked on pages that disallow `unsafe-eval`; `chrome_screenshot`, tab/navigation tools, and real input still work. +Strict CSP note: `chrome_snapshot`/`chrome_evaluate` work even on pages that disallow `unsafe-eval`, because they run via CDP `Runtime.evaluate` (not page-level `eval`/`new Function`), which is not subject to page CSP. `chrome_screenshot`, tab/navigation tools, and real input also work under any CSP. Chrome may show its debugger banner while pi-chrome is attached. diff --git a/docs/FAQ.md b/docs/FAQ.md index f821da7..3893575 100644 --- a/docs/FAQ.md +++ b/docs/FAQ.md @@ -55,7 +55,7 @@ pi-chrome controls web pages through Chrome extension APIs, page inspection, scr ## Does `chrome_evaluate` work on strict-CSP pages? -Not always. `chrome_evaluate` and `chrome_snapshot` run in the page's MAIN world through the Function constructor, so pages whose CSP blocks `'unsafe-eval'` can reject them. `chrome_screenshot`, `chrome_navigate`, tab tools, and real Chrome input still work because they use extension/browser APIs rather than page JavaScript. +Yes. `chrome_evaluate` and `chrome_snapshot` run in the page's MAIN world through CDP `Runtime.evaluate`, which is a DevTools protocol command and is **not** subject to the page's Content-Security-Policy. They work even on pages that block `'unsafe-eval'` (e.g. github.com and many bank/SaaS apps). `chrome_navigate`'s `initScript` injects at document_start via CDP and likewise bypasses CSP. `chrome_screenshot`, tab tools, and real Chrome input also keep working under any CSP. ## How do I tell whether a click or type worked? |