Organizations/security vendor

PromptArmor

2 records2 attack
Nov 20, 2025
PromptArmor shows Google Antigravity agent exfiltrating credentials from a poisoned web guide
AttackVulnerability disclosurePromptArmor, Google

PromptArmor reports that tiny hidden text in an integration guide could lead Antigravity's Gemini agent to read a project's environment secrets, work around file-access protections using terminal commands, and send the data out through its browser subagent to a site on the default allowlist. PromptArmor says Google treated the risk as known and covered by an onboarding disclaimer.

Aug 20, 2024
PromptArmor reports Slack AI can be steered to leak private-channel data via public-channel messages
AttackVulnerability disclosurePromptArmor, Salesforce

PromptArmor reports that instructions posted in a public Slack channel could be pulled into Slack AI answers for other users, enabling phishing links and leakage of data from private channels the attacker cannot read. The firm notes Slack's 2024-08-14 change to ingest files widened the surface, and that Slack described the underlying public-channel search as intended behavior.