Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/sgaabdu4/building-flutter-appsnpx agentmods add skills/sgaabdu4/building-flutter-apps/security-reviewWrote 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/skills/sgaabdu4/building-flutter-apps/security-review)<a href="https://agentmods.dev/skills/sgaabdu4/building-flutter-apps/security-review"><img src="https://agentmods.dev/badge/skills/sgaabdu4/building-flutter-apps/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.
<a href="https://agentmods.dev/skills/sgaabdu4/building-flutter-apps/security-review"><img src="https://agentmods.dev/badge/skills/sgaabdu4/building-flutter-apps/security-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00046 | $0.00534 |
| Opus 5.5 | $0.00018 | $0.00214 |
| Sonnet 5.5 | $0.00009 | $0.00107 |
| Haiku 4.5 | $0.00005 | $0.00053 |
Grade A, and why
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 18d 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.
What it actually says
Security Review
Load the review method; use Research when dependency/advisory claims need current evidence. Reuse existing fix/testing authority; review alone adds no remediation or live-exploitation authority.
flowchart LR
R[Code Review method] -->|Current dependency / advisory evidence| D[Research]
click R "../code-review/references/review.md"
click D "../research/SKILL.md"
- Trace = sensitive asset + caller/input + required permission → actual enforcing owner → operation/data. UI visibility or a caller's check does not prove server authorization.
- Coverage = focused change → affected path + adjacent callers; broad review → actual entry points + assets, then relevant surfaces below. Mark material missing evidence.
| Surface | Resolve |
|---|---|
| Identity / sessions | Caller-selected identity, role or tenant; login, recovery, expiry + revocation boundaries. |
| Data / privilege | Actor + tenant enforcement for object, field, list/export + mutation; alternate entry points. |
| Input / files | Query, markup, URL, path, upload/archive → normalization + downstream parser, fetch, storage or execution. |
| Secrets / artifacts | Source, logs, client bundle, generated config + packaged output exposure; inspect the actual in-scope artifact. Internal address alone ≠ secret. |
| LLM / tools | Untrusted content influencing privileged actions; permissions + validated arguments outside the model; required approval at the action boundary. |
| Dependencies | Resolved lockfile/image/SBOM/runtime version + existing scan + primary advisory ranges. Trace production/build/dev/transitive use; manifest range ≠ resolved version. Confirmed vulnerable version ≠ proven exploitability; unknown reachability never waives a required gate. |
- Finding = entry point + actor/input preconditions + enforcing/missing control + affected asset + realistic impact. Test competing explanations through source + permitted probes; unproven exploit path stays unknown.
- Secret evidence = type + location + exposure path; mask values. Keep findings, optional hardening + unresolved questions distinct.
- Authorized fix = smallest control satisfying the requirement; verify original unauthorized path denied + legitimate access preserved at the actual permission/input boundary. Run applicable gates.
- Result = assessed surfaces + findings + gaps. Scanner success proves only its checked scope; no whole-application certification or implied runtime proof.
What ships with it
1 file 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.
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.
- 18d ago First seen · 33 lines · 46 tokens per session scan A f9d62367226f
security-review is a skill published in the GitHub repository sgaabdu4/building-flutter-apps (25 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 534 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-29.
Other skills, from other repositories
fl-reviewer
Reviews UI-layer changes — screens, blocs, widgets, routes — against the template's StateBase + CoreBlocBase + fltheme conventions.
fl-data-reviewer
Reviews data-layer changes — Freezed DTOs, Retrofit clients, the storage seam, optional hivece stores, and repositories — against the template's conventions.
code-review
Use when asked to review a PR, MR, branch, or diff, audit changed files, or check code quality.
flutter-mcp-boundary-audit
Generic contract/schema boundary audit across authoring, discovery, validation, and execute—detecting split-brain between listings and invoke paths, gateway divergence, and permissive placeholders. Use when changing tool registration, RPC/plugin registries, dynamic tools, MCP or WebMCP surfaces, CLI exec aliases…
gitnexus-impact-analysis
Use when the user wants to know what will break if they change something, or needs safety analysis before editing code. Examples: "Is it safe to change X?", "What depends on this?", "What will break?".
fl-data-layer
Builds the data layer with Freezed DTOs, Retrofit clients, the storage-seam local data manager, and repositories wired through injectable.