When web content becomes an agent instruction
Threat research into indirect prompt injection on the public web, the agent boundaries that turn untrusted text into action, and the controls that break the chain.
Read articleBlog
Hands-on guides, original research, and product updates for securing AI agents in the real world, from the Signals Corps team.
Latest posts
Filter posts
Search post content, choose a product, or select one or more tags. Posts must match every active filter and at least one selected tag.
Logging in Claude Code: reconstruct prompts, actions, and results
A practical guide to Claude Code local records, OpenTelemetry, Compliance API transcripts, and prompt-to-action detections.
Logging in Codex: what did the agent actually do?
A practical guide to Codex local transcripts, OpenTelemetry, CODEX_LOG compliance files, and prompt-to-action detections.
No posts match those filters
Clear the filters or try a different search.