Snyk Agent Scan
open-sourceThe section your link pointed to isn't on Snyk Agent Scan's page any more, so we've brought you to the top.
Scans agent components (MCPMCPModel Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers, skills, harnesses) on a machine for prompt injections, tool poisoning, and vulnerabilities.
Summary
Snyk Agent Scan is an open-source command-line tool that discovers and scans agent components on a machine — MCP servers, skills, and harnesses — for prompt injections, tool poisoning, and other vulnerabilities. It is distributed via PyPI and free to use, run either as a one-off scan across all known MCP configs and skills or targeted at a single config or skill file, with a CI mode that auto-starts MCP servers for automated checks. It's aimed at teams building or operating AI agents who need to vet third-party skills and MCP integrations before trusting them, rather than at traditional application security scanning. Its README frames it around the emerging agent-skill ecosystem rather than positioning against a named competitor, so it sits in the newer category of AI agent and MCP security tooling.
Scans agent components (MCP servers, skills, harnesses) on a machine for prompt injections, tool poisoning, and vulnerabilities.
How Snyk Agent Scan helps
Which MCP servers and skills are actually configured on this machine right now?
walks every known MCP config location and skill directory and lists each server and skill it finds, before any security check runs
Does any installed skill or MCP server contain a prompt injection?
inspects the text and instructions bundled with each server and skill and flags the ones carrying hidden or malicious prompts
Is one of my configured tools trying to impersonate or override another trusted one?
checks each MCP server and skill for tool poisoning patterns and names the offending entry and the behavior it matched
Which of these components would fail a check before they ever get started in a pipeline?
runs the same scan in a mode that auto-starts each MCP server so the check happens against its real behavior rather than just its static config
What's configured in this one file I'm about to add, before it touches anything else?
scans a single targeted config or skill file in isolation and reports what it contains without needing a full-machine sweep
What does this component actually contain, apart from whether it's risky?
lists every MCP entity and skill file it discovered in full, separate from the security verdicts, so the raw inventory can be reviewed on its own
Languages
Command line
| option | found in | since | description |
|---|
Values are placeholders taken from each option’s declared default. Nothing is executed here — the output shown is a recording of a run that already happened.
Score card
-
Shipping velocity releases a month, last 12 months
-
Documentation quality release-notes rubric, 0–100
-
Breaking-change discipline how rarely a release breaks users, and notice given
-
Maintenance risk quiet time against its own cadence, maintainers
-
Innovation & surface new capabilities, API and MCP surface
- Community health
-
Contributor trend distinct committers, this year against last
-
Maintainer concentration bus factor now against a year ago
-
Issue backlog trend issues closed per issue opened, 12 months
-
Responsiveness median time to a maintainer’s first reply
Nine scores for Snyk Agent Scan, each built from the releases, notes and API history this site tracks — and, on Researcher and Business, where it stands among every measured tool in its category and how that has moved.
Score cards are part of every paid plan.
See plans → Already subscribed? Sign in →Trajectory
Blank means never measured; nothing here is a filled-in zero.
Peer standings are included with Researcher and Business. See how this tool ranks against its competitors, using data we don't publish anywhere else.
See plans →Each score is 0–100 on a published rubric, derived from data this site already shows. A dimension we cannot measure says so — it is never scored 0 and never enters a rank.
How this is scored
- Shipping velocity — releases a month over the last 12 months, on a log scale where 16 a month scores 100. Needs 3 releases in the window.
- Documentation quality — the release-notes rubric published on the analytics page, unchanged.
- Breaking-change discipline — the share of releases carrying a breaking change (none scores 100, half or more scores 0). Only projects that label breaking changes are measured: a clean record cannot be told from an unlabelled one.
- Maintenance risk — quiet time measured against the tool's own release cadence (quiet longer than 90 days and three typical gaps scores 0), plus the number of active maintainers and whether contributors are growing, where known. Higher is lower risk.
- Innovation & surface — new capabilities in the feature ledger this year, API and MCP operations added, and the share of commits that are features: the mean of whichever we hold.
- Community health (open-source tools only) — each is a direction, not a size: contributors this year against last, the bus factor now against a year ago, and issues closed per issue opened, where steady scores 50, doubled 100 and halved 0; plus the median time to a maintainer's first reply (an hour scores about 100, a month or more 0). A commercial card has no repository and carries none of the four.
- Documented delivery (commercial tools) — when a vendor's documented new capabilities have slowed against its own baseline, that counts against the overall standing as heavily as two low dimensions. Steady delivery, or too little history to judge, leaves the standing alone; it is never a sixth score.
- Open-source tools are scored on repository signals; commercial tools on their published changelog. Ranks compare tools within one category and one profile and need at least five measured peers; the overall standing needs three ranked dimensions. Best-in-breed or consolidator is a shape, not a quality, and is never scored.
Release-note detail over time
See how much detail Snyk Agent Scan puts in its release notes, quarter by quarter, and compare it with tracked tools in the same category. This history uses up to ten retained, reviewed notes per tool; sparse or blank older quarters may reflect that limit.
Checking release-note history…
Releases
Nothing shipped since we started watching. Releases and docs updates land here as they happen.
Project health
Issue, contributor and maintainer activity in snyk/agent-scan, 2023-10 – 2026-09, as of 2026-09-25. Twelve-month figures first; the trend lines run the whole window.
- Contributors 21 +10 vs prior 12 months
- Maintainers 7 +6 joined · −3 left, last 12 months
- Bus factor 3 committers behind half the commits
- Community-filed 100% of issues opened, last 12 months
- Median time to close 75 days first maintainer reply 17 days
- Open backlog 7 of 74 issues ever filed
- Issues opened / month 3 · 0 communitymaintainers
- Open backlog 7
- Contributors / month 7
- Commits / month 21
- Stars 3,077
- other 100%
Counts from the project's public repository and git history; no individuals are identified. Maintainers are the committers covering 80% of the last year's commits. how we measure this
Libraries its release ships
What its latest release locks, checked against known advisories.None of its release's images build from a lockfile we can read.
Add the badge to your README
Maintain this project? The badge links readers straight to this page, so they can follow every release here.
Choose a badge style and copy the code →