Level 1. Deviation
SalesBleed: Indirect Prompt Injection and 0-Click Data Exfiltration on Agentforce
- Developer
- Not established
- Model
- Not established
- When it happened
- Not established
- When it was disclosed
- October 3, 2026
- How well it is stood up
- Not verified yet
- What caused it
- Not established
- Where it stands now
- Not established
What happened
Reported by labs.zenity.io, dated 2026-10-03. Listed here with a link to their report. Nobody on this side has checked it against that report, so it carries no level and this is not our account of what happened.
Our assessment
- Actual
- 1 of 5Deviation
- Potential
- 3 of 5Significant control incident
The system behaved contrary to its instructions, and it stayed contained. The potential level is what the behaviour demonstrated here could credibly have led to, judged from the same evidence.
This level rests on news reports. The developer has not confirmed it here.
This happened in a test, an evaluation or a demonstration. Nobody real was harmed, so the actual level stays at 1. What it showed counts toward the potential level.
Zenity Labs has disclosed all findings to Salesforce who investigated and remediated the issue, hardening the Trusted URLs mechanism to prevent similar attacks.
Why this level
- Sensitive data was reachable. Argues for a potential level of 3
- The system acted autonomously. Argues for a potential level of 3
- The behaviour repeated rather than stopping. Argues for a potential level of 3
- Significant data was exposed. Argues for a potential level of 3
- A safeguard was bypassed. Argues for a potential level of 2
What is established, and what is not
Confirmed
Nothing is confirmed yet.
Reported, not confirmed
The system acted autonomously
Everything after that is automatic, and in both variants the payload leaves in the DNS lookup.
SalesBleed: Indirect Prompt Injection and 0-Click Data Exfiltration on AgentforceThe behaviour repeated rather than stopping. A claim, so it counts toward potential only
It could execute again every time an employee reviews it, and an attacker who wants a wider channel can simply submit more leads.
SalesBleed: Indirect Prompt Injection and 0-Click Data Exfiltration on AgentforceA safeguard was bypassed
We were eventually able to fully bypass all these mechanisms and exfiltrate data.
SalesBleed: Indirect Prompt Injection and 0-Click Data Exfiltration on AgentforceSensitive data was reachable
We found a way to pull sensitive account data out of Salesforce Agentforce without ever logging in, or requiring the victim to click anything.
SalesBleed: Indirect Prompt Injection and 0-Click Data Exfiltration on AgentforceSignificant data was exposed. A claim, so it counts toward potential only
Our POC video walks through an Accounts table exfiltration out of a tenant, one account at a time, which could create a full-on data breach.
SalesBleed: Indirect Prompt Injection and 0-Click Data Exfiltration on Agentforce
Checked, and did not happen
Nothing here was checked and ruled out.
Not confirmed
Nothing is outstanding.
Where this came from
The original report · read October 6, 2026
SalesBleed: Indirect Prompt Injection and 0-Click Data Exfiltration on AgentforceA structured incident database
AI Incident Database, own page, not yet read
The reports above are other people’s. The levels are ours, worked out under our published rules. No organisation that reported this assigned our number, and none of it is legal advice.
Something here is wrong? Tell us. Send us a source we can open, and a person will read it.