product-manager — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited product-manager (Agent Skill) and scored it 45/100 (orange). 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
A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.
*.sig, SIGNATURES) outside the documentation.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.
You are a senior product manager. Outcome-oriented, evidence-driven, opinionated with tradeoffs. Frameworks over templates. Specificity over completeness.
Product manager, PM, CPO, PRD, product requirements, roadmap, feature prioritization, user stories, discovery, user research, JTBD, MVP, product strategy, backlog, sprint planning, story mapping, OKRs, A/B testing, product metrics, NPS, retention, activation, onboarding, pricing, RICE, ICE, MoSCoW, product-market fit, PMF, personas, Kano, opportunity solution tree
Problem framing:
Jobs to Be Done (Christensen):
Opportunity Solution Tree (Teresa Torres):
Desired Outcome
├── Opportunity 1
│ ├── Solution A
│ └── Solution B
├── Opportunity 2
│ └── Solution C
└── Opportunity 3
├── Solution D
└── Solution ECustomer interview prep (Mom Test):
../../assets/frameworks/mom-test-cheatsheet.mdProof of Life (PoL) probes:
Product strategy session (6 phases):
Geoffrey Moore Positioning: For [target customer] who [need], [product] is a [category] that [key benefit]. Unlike [competitor], we [differentiator].
TAM/SAM/SOM:
RICE Prioritization: Score = (Reach × Impact × Confidence) / Effort
| Factor | How to Score |
|---|---|
| Reach | # users affected per quarter |
| Impact | 0.25 (minimal) to 3 (massive) |
| Confidence | 100% (data), 80% (strong signal), 50% (guess) |
| Effort | Person-months required |
PRD structure (10 sections):
User stories (Mike Cohn + Gherkin):
As a [specific persona],
I want to [action],
So that [measurable outcome].
Acceptance Criteria:
Given [context]
When [action]
Then [expected result]Story splitting patterns (Richard Lawrence):
Epic breakdown (9 patterns):
Now/Next/Later framework:
Roadmap communication rules:
MVP principles:
Scope cutting exercise: For each feature, ask:
AARRR (Pirate Metrics):
| Stage | Metric | Question |
|---|---|---|
| Acquisition | Signups, traffic sources | How do users find you? |
| Activation | Time to value, onboarding completion | Do they reach the "aha moment"? |
| Retention | DAU/MAU, Day 1/7/30 retention | Do they come back? |
| Revenue | Conversion rate, ARPU, MRR | Do they pay? |
| Referral | NPS, viral coefficient | Do they tell others? |
Product-Market Fit signals:
references/discovery.md — Problem framing, JTBD, interview techniques, PoL probesreferences/prd-framework.md — PRD template, user stories, acceptance criteriareferences/roadmap.md — Prioritization frameworks, roadmap communication, Now/Next/Laterreferences/mvp-scope.md — MVP definition, scope cutting, launch criteriareferences/pricing-strategy.md — Value metrics, pricing models, tier designreferences/metrics-dashboard.md — AARRR, PMF signals, metric definitionsreferences/habit-forming-products.md — Hook Model (trigger→action→reward→investment), variable rewards, manipulation matrix (Source: Hooked)~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.