Agentic Security
0.7.5 open-sourceThe section your link pointed to isn't on Agentic Security's page any more, so we've brought you to the top.
Agentic Security scans AI agents and LLMLLMA large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. applications for prompt injectionprompt injectionAn attack where text the model reads, such as a web page, file or tool result, carries instructions that override the user's. It is the main security risk for agents with tools., insecure tool usetool useA model's ability to answer with a structured request to run a named function or API, which the application executes and returns. It is how agents take actions., and other vulnerabilities.
curl -X POST /scan-csv -F 'file=@data.csv' from agentic_security.integrations import IntegrationProto print(IntegrationProto.__doc__) from agentic_security.cost import CostTracker cost = CostTracker() print(cost.calculate())
Summary
Agentic Security is an open-source command-line tool, free to use, that probes AI agents and LLM applications for prompt injection and insecure tool use rather than scanning source code or network endpoints the way older vulnerability scanners do. It targets AI engineers and red teamers who need to check an agent's behavior before it ships, running as a battery of adversarial tests rather than a passive linter. The category tags around it — llm-security, red-teaming — place it alongside emerging tooling for probing agent tool-use chains rather than the static-analysis scanners a security team might already own. It is under active development: first committed in 2024, it has drawn 31 contributors and seen 85 commits and 10 releases in the past year, suggesting the project is still being shaped rather than left to sit.
Agentic Security scans AI agents and LLM applications for prompt injection, insecure tool use, and other vulnerabilities.
How Agentic Security helps
Which prompt injection attempts actually get past this agent before a user finds them in production?
runs a battery of adversarial inputs against the agent and reports which ones changed its behavior or leaked instructions, rather than waiting for a linter to flag suspicious code
Which of my agent's tools could be tricked into running something the user never asked for?
drives adversarial prompts through each tool-use path and flags the calls that execute unintended actions, naming the tool and the input that triggered it
Is this agent safe to ship compared to how it behaved last time it was tested?
runs the same adversarial battery across versions and surfaces the cases whose outcome changed, rather than just a fresh pass/fail
Which parts of my LLM application trust user input in a way that turns into an insecure action downstream?
traces adversarial inputs through the request into whatever tool or system call they reach, and reports where untrusted text ends up controlling behavior
Where does an attacker only need one crafted message to make this agent ignore its own system prompt?
tests the agent with injection payloads aimed at overriding its instructions and reports which ones succeeded in changing its stated behavior
Languages
Command line
No command matches.
| 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 Agentic Security, 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 Agentic Security 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
7 entries
No entries match these filters.
- June 20261
- April 20251
- March 20251
- February 20253
- January 20251
Project health
Issue, contributor and maintainer activity in msoedov/agentic_security, 2023-10 – 2026-09, as of 2026-09-25. Twelve-month figures first; the trend lines run the whole window.
- Contributors 22 +6 vs prior 12 months
- Maintainers 2 +2 joined · −1 left, last 12 months
- Bus factor 1 committers behind half the commits
- Community-filed 69% of issues opened, last 12 months
- Median time to close 442 days first maintainer reply 6.6 days
- Open backlog 40 of 87 issues ever filed
- Issues opened / month 0 · 0 communitymaintainers
- Open backlog 40
- Contributors / month 7
- Commits / month 21
- Stars 2,004
- 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
Add the badge to your README
Maintain this project? The badge links readers straight to this page, so they can follow every release here.