agentic-security-review

agentic-security-review is a skill for Codex from browoz/agentic-sdlc-skills. It costs 106 tokens per session (546 once invoked), scanned A, original, MIT.

A security review skill for AI agents, tool connections, MCP and A2A integrations, and security-sensitive generated code. It checks dependencies, secrets, permissions, input handling, and risks from untrusted instructions or stored context.

In plain words
What is it for?
Use it to audit dependencies or code, inspect tool permissions and secrets, test agent-specific attack scenarios, and document findings with severity, evidence, and fixes.
Why use it?
AI systems can introduce risks through tools, packages, credentials, or misleading context as well as ordinary code. This review organizes those checks and identifies which issues should block release.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to audit dependencies or code, inspect tool permissions and secrets, test agent-specific attack scenarios, and document findings with severity, evidence, and fixes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/browoz/agentic-sdlc-skills/agentic-security-review
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 browoz/agentic-sdlc-skills --skill agentic-security-review
Clone the repo
git clone --depth 1 https://github.com/browoz/agentic-sdlc-skills

Made for: Codex.

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 agentic-security-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/browoz/agentic-sdlc-skills/agentic-security-review/github.svg)](https://agentmods.dev/skills/browoz/agentic-sdlc-skills/agentic-security-review)
Your own site
<a href="https://agentmods.dev/skills/browoz/agentic-sdlc-skills/agentic-security-review"><img src="https://agentmods.dev/badge/skills/browoz/agentic-sdlc-skills/agentic-security-review/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 agentic-security-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/browoz/agentic-sdlc-skills/agentic-security-review"><img src="https://agentmods.dev/badge/skills/browoz/agentic-sdlc-skills/agentic-security-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 546 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00106 $0.00546
Opus 5 $0.00053 $0.00273
Sonnet 5 $0.00021 $0.00109
Haiku 4.5 $0.00011 $0.00055

Measured 10d ago against content hash 8e6ad15d8ea8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

agentic-security-review 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 10d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/check_deps.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/agentic-security-review/SKILL.md · 56 lines

What it actually says

Agentic Security Review

Use this skill to find security risks introduced by agentic code, AI-generated changes, tool access, or untrusted context. Scope the review before scanning.

Workflow

  1. Determine scope:
    • deps-only: package declarations, lockfiles, imports.
    • code-only: secrets, auth, input handling, injection risks.
    • full: dependencies, code, tools, memory, context, red-team cases.
  2. Classify rigor:
    • Prototype: dependency and secret checks.
    • Internal: dependency, secret, input validation, and tool permission checks.
    • Production: full review plus context poisoning, CaMeL-style separation decision, red-team scenarios, and release blockers.
  3. Run scripts/check_deps.py <project-root> when Python files are present.
  4. Fill SECURITY_REVIEW.md from assets/templates/SECURITY_REVIEW.md.
  5. Mark findings with severity, evidence, file path, and concrete fix.
  6. Block release only for exploitable or high-impact issues; otherwise provide prioritized remediation.

Focus Areas

  • Dependencies: undeclared imports, unpinned direct dependencies, missing lockfile, suspicious package names.
  • Tools: shadowing, broad credentials, unsafe side effects, unclear provenance.
  • Code: CWE-20, CWE-78, CWE-89, CWE-327, hardcoded secrets, weak auth.
  • Context: prompt injection through external data, memory poisoning, unsafe tool responses, mixed trusted/untrusted data.

References

Read ../agentic-engineering-sdlc/references/day2_tools_and_interop.md for tool risks and ../agentic-engineering-sdlc/references/day4_security_and_evaluation.md for security/evaluation depth.

Done Criteria

  • Scope, rigor, and exclusions are documented.
  • Script output is attached or summarized when applicable.
  • Release blockers are separated from hardening recommendations.
  • Every high/critical finding has a reproduction path or clear evidence.
Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 56 lines · 106 tokens per session scan A 8e6ad15d8ea8

Subscribe to this mod's changes

agentic-security-review is a skill published in the GitHub repository browoz/agentic-sdlc-skills (3 stars, last pushed 2mo ago), licensed MIT. It adds 106 tokens to every session and 546 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories

create-custom-grader

Use when converting an existing benchmark, rubric, verifier, task YAML/JSON, or domain check into SkillEvaluator BYOG/BYOT custom evaluation.

NVIDIA/SkillEvaluator · 35 tokens

api-caller

Call any REST API dynamically. Make GET, POST, PUT, DELETE requests to any endpoint with custom headers and JSON body.

NVIDIA/SkillEvaluator · 29 tokens

calculator

Evaluate mathematical expressions and unit conversions. Handles arithmetic, percentages, exponents, and common unit conversions (temperature, distance, weight). No external dependencies.

NVIDIA/SkillEvaluator · 32 tokens

text-analyzer

Analyze text content and produce statistics including word count, line count, character count, most frequent words, and readability metrics. Works on any plain text input provided inline or from a file path.

NVIDIA/SkillEvaluator · 42 tokens

EMILIA Trust Verification

Verify the authenticity of AI-agent authorization receipts and human-device signoffs. Use this whenever a user shares a "trust receipt", an "authorization receipt", a "signoff", or WebAuthn/passkey approval evidence and asks whether it is valid, genuine, or tampered with. Pairs with the public EMILIA Protocol MCP…

emiliaprotocol/emilia-protocol · 94 tokens

building-agents

Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…

ericrisco/rsc-harness · 85 tokens