agent-security

agent-security is a skill for Claude Code from vikast908/agent-repo-card. It costs 102 tokens per session (1,367 once invoked), scanned A, original, MIT.

A security-review guide for applications that use AI models or autonomous agents. It checks how prompts, secrets, tools, data, and permissions could be abused.

In plain words
What is it for?
Use it to review an AI or agent application's code, assess risks using common security categories, and document evidence, severity, and fixes.
Why use it?
It helps find security weaknesses such as prompt injection, secret leaks, unsafe tool access, data theft, and excessive agent permissions.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to review an AI or agent application's code, assess risks using common security categories, and document evidence, severity, and fixes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vikast908/agent-repo-card/agent-security
Install

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.

Any agent
npx skills add vikast908/agent-repo-card --skill agent-security
Clone the repo
git clone --depth 1 https://github.com/vikast908/agent-repo-card

Made for: Claude Code.

Wrote 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.

agentmods badge for agent-security

README.md
[![agentmods](https://agentmods.dev/badge/skills/vikast908/agent-repo-card/agent-security/github.svg)](https://agentmods.dev/skills/vikast908/agent-repo-card/agent-security)
Your own site
<a href="https://agentmods.dev/skills/vikast908/agent-repo-card/agent-security"><img src="https://agentmods.dev/badge/skills/vikast908/agent-repo-card/agent-security/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for agent-security

Your own site · 80×15
<a href="https://agentmods.dev/skills/vikast908/agent-repo-card/agent-security"><img src="https://agentmods.dev/badge/skills/vikast908/agent-repo-card/agent-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,367 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00102 $0.01367
Opus 5 $0.00051 $0.00683
Sonnet 5 $0.00020 $0.00273
Haiku 4.5 $0.00010 $0.00137

Measured 9d ago against content hash 3ea4ad804c5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

agent-security scanned grade A with 2 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Tool surface:** what the agent can *do* — shell exec, file write/delete, HTTP requests, DB queries, payments, email/send, code eval. Search: `exec`, `spawn`, `subprocess`, `eval(`, `os.system`, `child_process`, `rm `

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- **Tool surface:** what the agent can *do* — shell exec, file write/delete, HTTP requests, DB queries, payments, email/send, code eval. Search: `exec`, `spawn`, `subprocess`, `eval(`, `os.system`, `child_process`, `rm `
skills/agent-security/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent / LLM security review

You are a security engineer specializing in LLM and agent applications. You think like an attacker who controls some of the model's input — a web page it reads, a document it summarizes, a tool result it receives — and you ask what that attacker can make the agent do. You review this repo against the OWASP Top 10 for LLM Applications plus classic appsec, and you only report issues you can ground in the code.

Scope: authorized defensive review of the user's own repo. If you find a real vulnerability, explain the risk and the fix — do not write a weaponized exploit.

Protocol (shared across all checks)

  1. Plan first (default). Present a short plan: the attack surfaces you'll inspect, the threat classes you'll check, the outputs, and assumptions/missing info. Ask "Proceed with the full security review, or adjust scope?" and wait. Skip if invoked with auto / "just do it".
  2. Evidence rule. Cite file:line. Quote ≤2 lines. Never invent a vuln; if a risk is theoretical for this code, label it unverified and say what would confirm it.
  3. Severity: Critical / High / Medium / Low (weigh exploitability × impact).
  4. Score dimensions below to 0–100 → grade.
  5. Output inline, then offer to save to agent-review/agent-security.md.

What to inspect

  • Trust boundaries: where untrusted text enters the model — user input, retrieved docs/RAG, web/page content, tool results, file contents, email/messages. Search: fetch, requests, retriev, scrape, read_file, parse.
  • Tool surface: what the agent can do — shell exec, file write/delete, HTTP requests, DB queries, payments, email/send, code eval. Search: exec, spawn, subprocess, eval(, os.system, child_process, rm , raw SQL, requests.get(url.
  • Secrets: API keys, tokens, credentials — in env vs hardcoded; whether secrets can reach the model context or logs. Search: api_key, secret, token, password, BEGIN PRIVATE KEY, .env.
  • Authz & multi-tenancy: can the agent/tool access another user's/tenant's data? Are tool actions scoped to the requesting user? Search for tenant/user IDs in queries.
  • Output handling: is model output rendered as HTML/markdown (XSS), executed, used in SQL, or passed to a shell without sanitization?
  • Prompt construction: is untrusted content concatenated into the system prompt or given the same authority as developer instructions? Is there separation between instructions and data?

Read the full file on GitHub · 65 lines

Changes

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.

  1. 9d ago First seen · 65 lines · 102 tokens per session scan A 3ea4ad804c5b

Subscribe to this mod's changes

agent-security is a skill published in the GitHub repository vikast908/agent-repo-card (1 stars, last pushed 2mo ago), licensed MIT. It adds 102 tokens to every session and 1,367 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

absolute-simplify

Use when the user wants to simplify, clean up, refactor, tidy, or refine code — their staged/unstaged git changes or a target file/path. Reduces complexity, flattens nesting, removes redundancy and dead code, scores each change by value (holding low-value churn), then runs tests to prove nothing broke. Invoke on…

maddhruv/absolute · 178 tokens

nasde-benchmark-runner

Run coding agent benchmarks and verify results with nasde. Use this skill when the user wants to: Run a benchmark (all tasks, single task, specific variant) Re-run assessment evaluation on existing trial results Check or verify results in Opik (traces, feedback scores, experiments) Troubleshoot a failed benchmark run…

NoesisVision/nasde-toolkit · 139 tokens

tactical-ddd

Design, refactor, analyze, and review code by applying the principles and patterns of tactical domain-driven design. Triggers on: domain modeling, aggregate design, 'entity', 'value object', 'repository', 'bounded context', 'domain event', 'domain service', code touching domain/ directories, rich domain model…

NoesisVision/nasde-toolkit · 70 tokens

nasde-benchmark-calibration

Calibrate assessment rubrics by reviewing agent work in GitHub/GitLab PRs and feeding human comments back into the rubric. Use this skill when the user wants to: Calibrate, tune, or sanity-check assessment criteria / dimensions of a benchmark Review trial diffs alongside the LLM-as-a-Judge scores in a PR/MR…

NoesisVision/nasde-toolkit · 171 tokens

nasde-dev

Internal skill for developing and maintaining nasde-toolkit itself. Use this skill when: Making changes to nasde-toolkit source code (CLI, runner, evaluator, config, agents) Refactoring or adding features to the toolkit Fixing bugs in the evaluation pipeline Updating dependencies or integration points (Harbor, Opik…

NoesisVision/nasde-toolkit · 103 tokens

python-best-practices

Provides Python patterns for type-first development with dataclasses, discriminated unions, NewType, and Protocol. Must use when reading or writing Python files.

NoesisVision/nasde-toolkit · 36 tokens