Skip to content
IAM Insights

Explainers · Glossary

Markdown

Markdown is a lightweight plain-text markup syntax that converts to HTML, used for documentation and agent instruction files.

reference →

In our briefings

The claim each of the newest briefings on Markdown would have you leave with.

  1. Singapore's IMDA offers agent identity practices for organisations to consider in the interim, and names the gaps that make them interim: today's authorisation systems typically use static scopes, and authentication systems, typically built around a single person, struggle when agents act for several users or spin up sub-agents. Each agent should have its own unique, cryptographically verifiable identity, tied to a supervising agent, a human user or a department. The capacity it acts in, such as on its own or for a named user, should be recorded, and every agent identity issued and tracked from a central system. Authorisations should generally be scoped, time- or session-bound, non-transferable and least-privilege, and, as a rule of thumb, a user should not be able to give an agent permissions beyond the user's own. IMDA points to OpenID's and the Cloud Security Alliance's agent identity papers for more.

    Singapore's regulator: each AI agent should have its own identity and, as a rule, no more access than its userBI-FIND-2026-0140

  2. The Agent Skills specification defines a skill as a folder holding a SKILL.md file whose frontmatter requires only a name and a description, followed by instructions with "no format restrictions." Nothing in the format lets an agent check who published a skill. The specification page never uses the words signature, hash, publisher, trust or security, and "author" and "version" appear only as sample keys in an optional metadata map of free-form strings. The one field about what a skill is allowed to run, allowed-tools, is a "Space-separated string of pre-approved tools the skill may use," marked Experimental, with support that "may vary between agent implementations." It sits in the skill's own frontmatter, and the page does not say who approves those tools or whether an agent may narrow the list. The validator it points to, skills-ref, checks that the frontmatter is valid and follows the naming conventions.

    The Agent Skills spec has no signature or publisher field, and a skill can list its own pre-approved toolsBI-FIND-2026-2266

  3. Woven by Toyota's AI agent sits at a new third step of the company's security-exception review, ahead of the human reviewer. Juan Corena says the outputs include a recommendation to approve, a recommendation to reject, or a request for more information with questions that may matter for granting it, and once the agent judges it has enough information the ticket goes to a human. His reason: "eventually a human needs to take the responsibility and understand all the consequences of what is being done there." He adds that simply asking whether a request complies with the standards would always get "no", since that is why it was requested, so the design had to allow for it.

    Woven by Toyota's exception agent recommends; a person decides, because a human has to answer for itBI-FIND-2026-2242

›Cited in 7 briefings

Every briefing that discusses this term, newest first.

  1. Singapore's regulator: each AI agent should have its own identity and, as a rule, no more access than its user

    Article · · Infocomm Media Development Authority (Singapore) · May 20, 2026

  2. The Agent Skills spec has no signature or publisher field, and a skill can list its own pre-approved tools

    Article · · Agent Skills · Aug 4, 2026

  3. Woven by Toyota's exception agent recommends; a person decides, because a human has to answer for it

    Video · · Agentic AI Foundation · Uploaded November 4, 2026

  4. From Level 2 up, OWASP's AI security standard asks for an identity per agent and a check on every MCP tool call

    Video · · OWASP Foundation · Oct 21, 2026

  5. Ping moved agent identity from roadmap to shipping product, and let AI agents run its admin tools too

    Conference · · Ping Identity · Austin · 2-day event (Day 1 / Day 2), 2026

  6. Stytch sells a one-call check for whether a visitor is an AI agent, priced at half a cent a lookup

    Podcast · · So What About AI Agents · EP 39 - Agentic Authentication | Bobbie Chen · Sep 23, 2025

  7. The 2023 paper that named indirect prompt injection showed an attacker can use whatever access the assistant has

    Paper · · arXiv (cs.CR) · Kai Greshake et al. · Feb 23, 2023