AC security-repro
Build safe, local, defensive reproductions of ALREADY-PATCHED, publicly disclosed security vulnerabilities (CVEs, vendor advisories, AI-agent incidents) for whitepapers, control testing, and education. Use this skill whenever the user wants to reproduce, demonstrate, or write up a known vulnerability or security incident — phrases like "reproduce this CVE", "build a repro for", "demonstrate the EchoLeak/Cursor/postmark-mcp issue", "show how this exploit worked", "add a reproducibility guide", or "pull the NVD/CVE details for". It fetches advisory metadata from NVD and CVE.org, confirms the issue is fixed, and produces a vulnerable-vs-patched harness that is offline, loopback-only, and uses synthetic markers. It NEVER discovers, develops, or weaponizes new zero-days and refuses any unpatched or live-target request.
The skill promises to build local reproductions of already-patched CVEs for whitepapers and control testing. The description cuts off mid-sentence, suggesting incomplete documentation. Five files, three scripts, fifteen hundred body tokens—reasonable volume for the task.
Checks returned grade A with 93% quality, but process score of 58% signals gaps in reproducibility or testing. No critical findings, linter passed. Model runs and sandbox untested. Supports nine platforms including Claude and Cursor.
The catch: unclear how it verifies a vulnerability is actually patched, and isolation reliability remains opaque. Install if you accept incomplete docs and are prepared for runtime behavior to diverge from promises.
Build safe, local, defensive reproductions of ALREADY-PATCHED, publicly disclosed security vulnerabilities (CVEs, vendor advisories, AI-agent incidents) for…
As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 58/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 100Steps. 15 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1497 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 825: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +4Structure: 10 headings
- +3Step-by-step instructions: 15 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.