SkillsBench is a benchmark for measuring how effectively AI agents use modular skills—folders containing instructions, scripts, and resources—to complete specialized tasks. It helps researchers and developers evaluate both skill quality and agent behavior, including tasks that require combining multiple skills. The catalogue’s skills and instructions are evaluated as part of this workflow.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add benchflow-ai/skillsbench --skill jackson-securitygit clone --depth 1 https://github.com/benchflow-ai/skillsbenchWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/benchflow-ai/skillsbench/jackson-security)<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/jackson-security"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/jackson-security.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00031 | $0.00844 |
| Opus 5 | $0.00015 | $0.00422 |
| Sonnet 5 | $0.00006 | $0.00169 |
| Haiku 4.5 | $0.00003 | $0.00084 |
Grade B, and why
jackson-security scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
"command": "rm -rf /" Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Copies of this mod
1 near-identical copy found in the catalogue:
- jackson-security — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jackson Deserialization Security
Key Concept: Deserialization Timing
Jackson transforms JSON text into Java objects during a single readValue() call. This transformation is not a simple data copy—Jackson interprets JSON structure, resolves types, handles special keys, and instantiates objects all within this operation.
JSON String → [Jackson Processing] → Java Object
↑
Attack surface here
Once deserialization completes, the resulting Java object contains no trace of how it was constructed. Any special JSON structures, unusual keys, or type directives that influenced object creation are no longer visible.
Why Post-Deserialization Validation Is Insufficient
Consider the lifecycle of a typical JSON endpoint:
1. HTTP request arrives with JSON body
2. Framework deserializes JSON → Java object (Jackson runs here)
3. Your code receives the Java object
4. Your code validates the object
5. Your code processes the object
Validation at step 4 examines the result of deserialization, not the process. Any malicious behavior triggered during step 2 has already executed. The Java object you're validating may appear completely normal while the attack has already succeeded.
This creates a fundamental blind spot: attacks that exploit Jackson's parsing behavior—rather than the final object state—cannot be detected by examining the deserialized object.
The Empty Key ("") Attack Vector
What Is It?
JSON permits empty strings as object keys:
{
"name": "legitimate",
"": "injected value"
}
This is valid JSON per RFC 8259. Jackson parses it without error.
Why Does It Matter?
Some applications and frameworks assign special meaning to empty keys:
- Injection points: Certain Jackson configurations use
""to set values on the root object or trigger special handling - Property override: Empty keys may interact unexpectedly with
@JsonAnySetteror custom deserializers - Framework behaviors: Some frameworks interpret
""as "apply to parent" or "default target"
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 113 lines · 31 tokens per session scan B 302271926534
jackson-security is a skill published in the GitHub repository benchflow-ai/skillsbench (1,747 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 844 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
jackson-injection-security
Security considerations for Jackson @JacksonInject - preventing JSON input from overriding injected values, covering CVE patterns and defense strategies.
java-patch-workflow
Workflow for creating and applying patches to Java projects - diff format, patch application, and Maven rebuilds for security fixes.
azure-security-keyvault-secrets-java
Azure Key Vault Secrets Java SDK for secret management. Use when storing, retrieving, or managing passwords, API keys, connection strings, or other sensitive configuration data.
azure-ai-anomalydetector-java
Build anomaly detection applications with Azure AI Anomaly Detector SDK for Java. Use when implementing univariate/multivariate anomaly detection, time-series analysis, or AI-powered monitoring.
azure-communication-chat-java
Build real-time chat applications with Azure Communication Services Chat Java SDK. Use when implementing chat threads, messaging, participants, read receipts, typing notifications, or real-time chat features.
azure-communication-common-java
Azure Communication Services common utilities for Java. Use when working with CommunicationTokenCredential, user identifiers, token refresh, or shared authentication across ACS services.