BD skill-mcp-security-audit
Security audit for MCP (Model Context Protocol) servers. Detect data exfiltration risks, command injection, permission escalation, and supply chain vulnerabilities before adding MCP servers to your agent. Trigger on: 'audit MCP', 'MCP security', 'check MCP server', 'scan MCP'.
As a process D 48/100 · Unfinished process — 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 · 9
✓ No critical or high findings
Medium and low: 9
-
low Risky intent
intent-offensive-securityREADME.md:19Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- ⚡ **Chain vulnerabilities** for privilege escalation
-
low Risky intent
intent-offensive-securityREADME.md:50Offensive-security / dual-use content (legitimate for authorised testing; review intended use)│ 🔑 Perms │ Excessive scope? Missing consent? Privilege escalation?
-
low Dangerous commands
cmd-eval-dynamicREADME.md:95Dynamic code execution from decoded/untrusted input (documentation of a security skill)eval(atob('YWxl…lKQ=='))security skill -
low Risky intent
intent-offensive-securityREADME.md:100Offensive-security / dual-use content (legitimate for authorised testing; review intended use)// Credential harvesting — sends your secrets to an external server
-
low Risky intent
intent-offensive-securitySKILL.md:20Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **Chain vulnerabilities** for privilege escalation
-
low Dangerous commands
cmd-eval-dynamicSKILL.md:132Dynamic code execution from decoded/untrusted input (negated — the text forbids it)1. **Obfuscated code** - `eval(atob('...'))` or similarnegated -
low Risky intent
intent-offensive-securitySKILL.md:135Offensive-security / dual-use content (legitimate for authorised testing; review intended use)4. **Credential harvesting** - Asking for passwords/tokens unnecessarily
A further 2 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Security audit for MCP (Model Context Protocol) servers. Detect da… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 48/100
- 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
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (skill-mcp-security-audit) differs from the folder (mcp-security-audit)
- 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
- 100Execution cost. Instruction body is 1457 tokens
- low 10 top-level sections: this looks like several domains in one skill
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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 277: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 15 items
- +4Has examples (12 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.