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.
/plugin marketplace add balsm-health/Balsm-AInpx agentmods add plugins/balsm-health/balsm-ai/plugingit clone --depth 1 https://github.com/balsm-health/Balsm-AIWrote 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/plugins/balsm-health/balsm-ai/plugin)<a href="https://agentmods.dev/plugins/balsm-health/balsm-ai/plugin"><img src="https://agentmods.dev/badge/plugins/balsm-health/balsm-ai/plugin.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
balsm-ai 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What it installs
The manifest is a name and a version. 53 skills, 1 command, 1 agent, 2 hooks, 3 MCP servers travel with it, and installing the plugin installs all of them — 3,603 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill design-taste-frontend A 61 tokens
- Skill image-to-code A 116 tokens
- Skill imagegen-frontend-mobile A 126 tokens
- Skill imagegen-frontend-web A 126 tokens
- Skill design-taste-frontend-v1 A 61 tokens
- Skill implementing-hashicorp-vault-dynamic-secrets A 74 tokens
- Skill brandkit A 89 tokens
- Skill domain-driven-design A 136 tokens
- Skill exploiting-broken-function-level-authorization A 108 tokens
- Skill exploiting-excessive-data-exposure-in-api A 114 tokens
- Skill implementing-api-rate-limiting-and-throttling A 114 tokens
- Skill analyzing-email-headers-for-phishing-investigation A 44 tokens
- Skill balsm-ai-governance A 164 tokens
- Skill conducting-cloud-incident-response A 76 tokens
- Skill detecting-misconfigured-azure-storage A 52 tokens
- Skill detecting-s3-data-exfiltration-attempts A 63 tokens
- Skill exploiting-idor-vulnerabilities A 33 tokens
- Skill exploiting-insecure-deserialization A 37 tokens
- Skill exploiting-sql-injection-vulnerabilities A 108 tokens
- Skill extracting-iocs-from-malware-samples A 82 tokens
- Skill implementing-cloud-security-posture-management A 59 tokens
- Skill implementing-secrets-management-with-vault A 69 tokens
- Skill detecting-container-escape-attempts A 40 tokens
- Skill exploiting-http-request-smuggling A 34 tokens
- Skill exploiting-mass-assignment-in-rest-apis A 41 tokens
- Skill high-end-visual-design A 53 tokens
- Skill implementing-aws-iam-permission-boundaries A 34 tokens
- Skill industrial-brutalist-ui A 57 tokens
- Skill analyzing-indicators-of-compromise A 106 tokens
- Skill analyzing-ios-app-security-with-objection A 49 tokens
- Skill balsm-design A 0 tokens
- Skill exploiting-deeplink-vulnerabilities A 95 tokens
- Skill exploiting-insecure-data-storage-in-mobile A 104 tokens
- Skill gpt-taste A 72 tokens
- Skill hardening-docker-containers-for-production A 43 tokens
- Skill minimalist-ui A 34 tokens
- Skill hunting-for-persistence-mechanisms-in-windows A 36 tokens
- Skill implementing-secrets-scanning-in-ci-cd A 30 tokens
- Skill domain-driven-design-planner A 81 tokens
- Skill hunting-for-unusual-network-connections A 36 tokens
- Skill hunting-for-webshell-activity A 39 tokens
- Skill analyzing-android-malware-with-apktool A 50 tokens
- Skill analyzing-kubernetes-audit-logs A 71 tokens
- Skill detecting-credential-dumping-techniques A 42 tokens
- Skill detecting-supply-chain-attacks-in-ci-cd A 69 tokens
- Skill full-output-enforcement A 44 tokens
- Skill implementing-api-key-security-controls B 98 tokens
- Skill exploiting-server-side-request-forgery B 34 tokens
- Skill exploiting-sql-injection-with-sqlmap B 31 tokens
- Skill exploiting-nosql-injection-vulnerabilities B 43 tokens
- Skill hardening-docker-daemon-configuration B 36 tokens
- Skill analyzing-memory-dumps-with-volatility C 80 tokens
- Skill analyzing-linux-system-artifacts E 35 tokens
- Command balsm-context A 18 tokens
- Agent balsm-reviewer A 56 tokens
- Hook PreToolUse A not measured
- Hook UserPromptSubmit A not measured
- MCP server github A not measured
- MCP server supabase A not measured
- MCP server sentry A not measured
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 · 10 lines scan A e30446e784cc
balsm-ai is a plugin published in the GitHub repository balsm-health/Balsm-AI (2 stars, last pushed 21d ago), with no licence file. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.
Other plugins, from other repositories
google-plugins marketplace
Plugin marketplace listing 17 plugins: alloydb, alloydb-omni, bigtable, cloud-sql-mysql, cloud-sql-postgresql.
hana-cli
150+ SAP HANA database tools for AI assistants. Query tables, import/export data, profile data quality, compare schemas, manage backups, monitor performance, and more. Connects to SAP HANA Cloud and on-premise databases.
butterbase-skills
Build full-stack apps with Butterbase — AI-Native Backend-as-a-Service. Skills for app creation, schema design, frontend deployment, RLS debugging, serverless functions, and contributing.
sql-database-pipeline
Build SQL database pipelines with dlt: connect to any SQL source, load tables to a destination, tune performance with backends.
sap-abap
Comprehensive ABAP development skill for SAP systems. Use when writing ABAP code, working with internal tables, structures, ABAP SQL, object-oriented programming, RAP (RESTful Application Programming Model), CDS views, EML statements, ABAP Cloud development, string processing, dynamic programming, RTTI/RTTC, field…
reporting-and-database-access
MATLAB, Database Toolbox, MATLAB Report Generator, Parallel Computing Toolbox, and Simulink Report Generator.