AIToday
Large Language ModelsAI Coding AssistantsZenn AI/MLPublished: Nov 22, 2026, 16:00 JST

Nishito: AI agent blocked daily script over 'source .venv' and HTTP 403

Send on LINE
Nishito: AI agent blocked daily script over 'source .venv' and HTTP 403

3 Key Points

  1. What happened

    Nishito's morning script failed with HTTP 403 from a local proxy, then a pre-tool hook block; the cause was human-style shell lines like source .venv/bin/activate and $(date), not a site outage.

  2. Why it matters

    Human-style shell lines like source .venv/bin/activate and $(date) disable automatic prefix approval and trigger extra review, so scripts that worked yesterday can stop without any code change.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, every morning.

Context & Analysis

The incident described by Nishito shows how AI coding agents have quietly added security layers that can trip up scripts written for human terminal habits. The first layer, an OS-level sandbox with a local proxy, returned HTTP 403 because the target domain was not on the allowed list. The second layer, a syntax-analysis parser, refused to auto-approve chained commands and command substitutions, because such patterns could hide arbitrary code. The third layer, a pre-execution AI classifier, saw a sandbox bypass attempt right after a policy denial and issued a hard block. Nishito notes that Anthropic research cited by Backslash Security found developers approve 93% of confirmation prompts, which helps explain why agents now run independent review models before tool calls. The practical takeaway is that skill files should be written as single, pinned commands with no shell chaining or substitution, and that write operations should stay behind human approval. Nishito also recommends moving scheduled runs to CI/CD or ephemeral containers for enterprise use, since local tamper prevention has limits.

FAQ
Why did the script get an HTTP 403 error?
The OS sandbox routes network traffic through a local proxy that returns HTTP 403 for domains not on the allowedDomains list; it was not the target site blocking the request.
What does BypassSandbox: true do?
It runs a command outside the standard OS sandbox, which Nishito found necessary for headless browser steps because local WebSocket connections and browser processes hang inside the isolated network namespace.
How did Nishito fix the skill?
He rewrote SKILL.md to use a single pinned command (.venv/bin/python3 run_daily_verification.py) without cd, source, or $(date), added deny rules against editing the script and .venv, and kept human approval for write operations like S3 uploads.
Send on LINE

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.

Questions and answers are published on this page.

Related Articles

Next articleJerry Newman: AI's Big Winners May Not Be AI Companies