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 cxcscmu/SkillLearnBench --skill jackson-securitygit clone --depth 1 https://github.com/cxcscmu/SkillLearnBenchWrote 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/cxcscmu/skilllearnbench/jackson-security)<a href="https://agentmods.dev/skills/cxcscmu/skilllearnbench/jackson-security"><img src="https://agentmods.dev/badge/skills/cxcscmu/skilllearnbench/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 | $0.00024 | $0.00458 |
| Opus 5 | $0.00012 | $0.00229 |
| Sonnet 5 | $0.00005 | $0.00092 |
| Haiku 4.5 | $0.00002 | $0.00046 |
Grade A, and why
jackson-security scanned grade A with 0 findings 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Jackson Security: @JacksonInject and Property Overrides
In Jackson, @JacksonInject is used to inject values from the InjectableValues of the ObjectMapper. However, by default, if a property with the same name exists in the JSON, it might override the injected value, or Jackson might try to bind the JSON property to that parameter.
Vulnerability: Injected Value Override
If an attacker can provide a property in the JSON that matches the name of an injected parameter, they might be able to control that parameter.
Example
public class MyObject {
private final String secret;
private final boolean enabled;
@JsonCreator
public MyObject(
@JsonProperty("secret") String secret,
@JacksonInject boolean enabled
) {
this.secret = secret;
this.enabled = enabled;
}
}
If the InjectableValues has enabled = false, but the JSON is {"secret": "foo", "enabled": true}, Jackson might set enabled to true.
Mitigation: useInput = false
To prevent this, you should set useInput = false in the @JacksonInject annotation.
@JsonCreator
public MyObject(
@JsonProperty("secret") String secret,
@JacksonInject(useInput = false) boolean enabled
) {
// ...
}
When useInput = false, Jackson will ONLY use the injected value and will ignore any value for this property in the JSON input.
The Empty Key "" Bypass
In some versions of Jackson or specific configurations, an empty key "" might be treated specially, sometimes being mapped to the "default" or "root" of some internal structure, potentially bypassing name-based checks or matching unnamed injected parameters.
If a @JacksonInject is used without a name, Jackson might use the type name or parameter name. If an attacker uses "", it might under certain circumstances be matched to an unnamed or specifically named injectable.
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 · 55 lines · 24 tokens per session scan A 5d36a58e4370
jackson-security is a skill published in the GitHub repository cxcscmu/SkillLearnBench (83 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 458 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
hotpath_bump
Bump the hotpath version number across the workspace and related files. Updates crate versions in Cargo.toml files (exact patch version) and version references in the backend middleware, hotpathinit skill, and README (major.minor only). Use when the user wants to bump, bump the version, or release a new hotpath…
agentsop-http-tool-wrapping
Decision protocol for wrapping a REST / GraphQL / RPC API as a tool an LLM agent can call. The load-bearing premise: the tool surface is an LM-friendly subset of the API surface — one tool per user intent, not one per endpoint. Activates when a coder agent must expose an external HTTP API to a model (function calling…
agentsop-streaming-output
Enhancement-overlay decision protocol for STREAMING the output of long-running LLM / agent runs from the backend, not just wiring a typing animation in the UI. Activates when a coder agent must stream final tokens to a chat client, surface intermediate agent steps (which tool, which node, partial reasoning), emit…
erlang-distribution
Use when erlang distributed systems including node connectivity, distributed processes, global name registration, distributed supervision, network partitions, and building fault-tolerant multi-node applications on the BEAM VM.
Model Serving
Serve local or remote ML models behind inference endpoints.
run-inferbench-backend
Build, launch, smoke-test and drive the InferBench FastAPI backend (:7777) and its inference-engine orchestration. Use when asked to run, start, launch, boot, smoke-test, benchmark, or drive the inferbench backend / API / engines (llama.cpp, ollama, vLLM, SGLang, TGI), or to verify an engine actually starts and runs a…