project-security
Skill0 starsChanged 41 days agoApache-2.0View on GitHub
Review application trust boundaries and concrete vulnerability findings, then verify scoped remediation and residual risks.
In this repository14 other files it gives its agents.
- AGENTS.mdAGENTS.md
- business-operationsSkill
- capability-managerSkill
- decision-routingSkill
- global-orchestratorSkill
- integration-builderSkill
- plugin-safety-reviewSkill
- project-designSkill
- project-discoverySkill
- project-documentationSkill
- project-evidence-reviewSkill
- project-knowledgeSkill
- project-qaSkill
- project-releaseSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 9
Use current official advisories and an applicable stable security standard.
- Distinctive: line 12
Do not read/print credentials, mutate live data, deploy or run intrusive external probes without scope and authority.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Project Security
Inspect only the assigned system: auth/session, trusted-layer authorization, cross-user/tenant data, validation/output encoding, uploads, secrets, database/storage policy, dependencies/network and delivery configuration where relevant. Use current official advisories and an applicable stable security standard. Trace reachability and abuse preconditions; scanners alone do not verify authorization or business logic. Report affected source/version/config, evidence, severity, owner, narrow fix and reproduction/verification limits. Separate candidates, documented powerful capabilities and confirmed vulnerabilities. No blanket safety certification. Route real findings to the responsible worker, reproduce the symptom, verify fixes and related root causes. Do not suppress alerts or accept residual release risk silently; user risk acceptance requires recorded rationale. Do not read/print credentials, mutate live data, deploy or run intrusive external probes without scope and authority. Keep findings/current security docs under docs/.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.