ia-document-review — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited ia-document-review (Agent Skill) and scored it 91/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 1 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
The text {match} is the classic direct prompt-injection phrasing. Placed in a skill body that the agent reads as trusted instructions, it tries to make the agent abandon its prior rules and follow whatever comes next — a full system-prompt override.
ignore/disregard/forget … previous instructions sentence.Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Improve brainstorm or plan documents through structured review.
If a document path is provided: Read it, then proceed to Step 2.
If no document is specified: Ask which document to review, or look for the most recent brainstorm/plan in docs/brainstorms/ or docs/plans/.
Read through the document and ask:
These questions surface issues. Don't fix yet--just note what you find.
Based on the document's content, activate specialized review perspectives. Scan for signals and apply matching lenses:
| Lens | Signals | What it checks |
|---|---|---|
| Product | User-facing features, customer language, market claims, scope decisions | Problem framing, value proposition clarity, whether scope matches stated goals |
| Design | UI/UX references, user flows, wireframes, interaction descriptions | Flow completeness, interaction gaps, accessibility considerations |
| Security | Auth/authorization, API endpoints, PII, payments, tokens, encryption | Auth model gaps, data exposure risks, missing threat considerations |
| Scope guardian | Multiple priority tiers (P0/P1/P2), large requirement count (>8), stretch goals | Scope creep, premature abstractions, features disguised as requirements |
| Adversarial | >5 distinct requirements, explicit architectural decisions, high-stakes domains | Unstated assumptions, optimistic estimates, single points of failure, missing failure modes |
Activate a lens when ANY of its signals match. Most documents trigger 1-2 lenses; brainstorm notes may trigger none. When a lens is active, weave its checks into the assessment and evaluation steps rather than running it as a separate pass.
Score the document against these criteria:
| Criterion | What to Check |
|---|---|
| Clarity | Problem statement is clear, no vague language ("probably," "consider," "try to") |
| Completeness | Required sections present, constraints stated, open questions flagged |
| Specificity | Concrete enough for next step (brainstorm → can plan, plan → can implement) |
| YAGNI | No hypothetical features, simplest approach chosen |
If invoked within a workflow (after /ia-brainstorm or /ia-plan), also check:
Among everything found in Steps 2-4, does one issue stand out? If something would significantly improve the document's quality, this is the "must address" item. Highlight it prominently.
Present your findings, then:
Simplification is purposeful removal of unnecessary complexity, not shortening for its own sake.
Simplify when:
Don't simplify:
For standalone documents that must be self-contained (onboarding guides, ADRs, external-facing docs), dispatch a zero-context sub-agent to simulate a first-time reader. The sub-agent has no conversation history — it sees only what a future reader would see.
How to run the test:
Interpret results:
Skip for context-dependent docs (brainstorm notes, plan files, internal working docs) where the reader will always have prior context. The sub-agent test only adds value when the real reader has no other channel.
After changes are complete, ask:
After 2 refinement passes, recommend completion--diminishing returns are likely. If the user wants to continue, allow up to 4 passes total. After 4, stop and report "review converged -- further changes require new direction." Do not continue past 4 even on user request without a fresh framing.
Return control to the caller (workflow or user) after selection.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.