Felt worth asking another agent a couple of quick q's here!

Codex isn't so optimistic, it sees documentation that the community is telling you to do acrobatic things to not be susceptible to hacks from 3 years ago:

---

› heyo codex, find the clawdbot git repo, clone it into ~/Work/clawdbot , and research how it handles prompt injection attacks from data it gets, eg, when it crawls webpages for the user. for example, does it wrap foreign non-user input with <untrusted-UUID123>...payload...</untrusted-UUID123> when the prompt gets constructed?

─ Worked for 9m 08s ────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────

• Cloned the repo to /home/lmeyerov/Work/clawdbot and reviewed the web-fetch/browser tooling plus security docs. Short answer: I found no <untrusted-…> wrapping or similar tagging in prompt construction or tool outputs.

  Findings

  - web_fetch extracts HTML into markdown/text, strips script/style/noscript, and truncates output, but returns the content as plain text inside a JSON tool result; the tool wrapper
    just stringifies JSON (no untrusted tags). See src/agents/tools/web-fetch.ts:446, src/agents/tools/web-fetch.ts:549, src/agents/tools/web-fetch-utils.ts:28, src/agents/tools/
    common.ts:171.
  - browser snapshots return raw snapshot text (or an image + text) as the tool result; again, no wrapper tags. See src/agents/tools/browser-tool.ts:568.
  - Prompt-injection mitigation is documented as operational policy: treat external content (web search/fetch/browser pages) as untrusted, use reader agents, disable web tools for
    tool-enabled agents, sandbox aggressively, and use stronger models. See docs/gateway/security.md:191, docs/help/faq.md:2572.
  - There is a plugin hook to transform tool results before persistence if you want to add your own wrappers, but it’s not used by default. See docs/hooks.md:238.

› so would normal usage of just install clawdbot and asking it to look at a webpage risk prompt injection, and if not, why not?

• Yes — it still risks prompt injection when you ask it to look at a webpage. The web content is returned as plain text in tool results (no <untrusted> wrappers), so adversarial instructions can land directly in the model context; see src/agents/tools/web-fetch.ts:446, src/agents/tools/browser-tool.ts:568, src/agents/tools/common.ts:171. The docs explicitly say prompt injection is not solved and that web content is untrusted, with mitigations being reader agents, disabling web tools for tool‑enabled agents, and sandboxing; see docs/ gateway/security.md:191, docs/help/faq.md:2572. Also, the default main session runs tools on the host, so if the model is tricked the blast radius can include real tool calls; see README.md:317.