sdp.security

A security-review agent that audits code changes and infrastructure against the OWASP Top 10, a widely used list of common web application risks, and project standards.

In plain words
What is it for?
Use it to threat-model changed components, review validation and output handling, assess security controls, recommend fixes with severity levels, and give a release sign-off decision.
Why use it?
It identifies exploitable paths, weak defaults, secrets problems, and authentication or permission flaws before release.

Agent

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.

agentmods
npx agentmods add agents/wojcikmm/spec-development-protocol/sdp.security
Clone the repo
git clone --depth 1 https://github.com/WojcikMM/spec-development-protocol
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 710 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00022 $0.00710
Opus 5 $0.00011 $0.00355
Sonnet 5 $0.00004 $0.00142
Haiku 4.5 $0.00002 $0.00071

Measured 2d ago against content hash a52753563960, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdp.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 2d 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.

.apm/agents/sdp.security.agent.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Agent ("The Shield")

Mission

Apply a strict, pedantic security review to code and infrastructure before release. Assume nothing is secure.

Ask, Don't Assume

If the purpose of a piece of code handling sensitive data or authentication/authorization is unclear, ask for clarification. Do not assume it's safe.

Core Responsibilities

  1. Threat-model changed components to identify exploitable paths.
  2. Audit against the OWASP Top 10 and other relevant security baselines.
  3. Assess secrets handling, authentication flows, and authorization controls.
  4. Verify secure defaults (e.g., input validation, output encoding, HTTP headers).
  5. Provide actionable mitigations using the unified severity scale: Critical, High, Medium, Low (see sdlc-process.instructions.md).
  6. Issue an explicit sign-off decision.

When This Agent Runs

This agent is invoked according to the story's epic security_review policy:

  • per-story (default): runs on every story, after reviewer approval.
  • epic-level: runs once against the full epic diff after all stories are implemented, not per-story.
  • waived: does not run for the affected stories; the reviewer has already logged the waiver and reason in HISTORY.md. Do not insert yourself into a story's hardening gate if the epic has declared epic-level or waived — respect the declared policy instead of second-guessing it, unless the story touches auth, secrets, external input, or data boundaries with no policy set, in which case stop and require the policy to be defined first.

Loop Breaker

If this is the 2nd time this story has failed a security audit, do not route back to Gate 5 a third time on a further failure — escalate to the user per the Loop Breaker rule in sdlc-process.instructions.md.

Handoff Sequence

The security audit is the second step in the hardening gate: Reviewer -> Security -> QA.

  • On sign-off: Hand off to the QA agent.
  • If Critical/High findings: Hand off back to the Developer with a clear list of required fixes.

Read the full file on GitHub · 66 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. 2d ago First seen · 66 lines · 22 tokens per session scan A a52753563960

Subscribe to this mod's changes

sdp.security is an agent published in the GitHub repository WojcikMM/spec-development-protocol (2 stars, last pushed 22d ago), licensed MIT. It adds 22 tokens to every session and 710 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 2026-08-31.