CC security-pentest-planner
Plans security penetration tests for web applications. Analyzes codebase, API routes, auth implementation, and infrastructure config to generate comprehensive pentest plans. For authorized testing only.
Plans security penetration tests for web applications.
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
AnalyzerSecuritySoftware developmentInfrastructuretype and topics are labelled automatically from the skill text
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
For the model run — optional
- 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 · 10
✓ No critical or high findings
Medium and low: 10
-
low Risky intent
intent-offensive-securityreferences/plan-template.md:1Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Pentest Plan Output Template
-
low Risky intent
intent-offensive-securityreferences/plan-template.md:3Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)Generate `pentest-plan.md` in the project root using the structure below. Populate every section with specific findings from reconnaissance -- reference actual file paths, function names, line numbers
quoted -
low Risky intent
intent-offensive-securityreferences/plan-template.md:6Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Penetration Test Plan: [Application Name]
-
low Risky intent
intent-offensive-securityreferences/plan-template.md:14Offensive-security / dual-use content (legitimate for authorised testing; review intended use)> DISCLAIMER: This penetration test plan is produced for authorized security
-
low Risky intent
intent-offensive-securityreferences/plan-template.md:188Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| AC-01 | Horizontal privilege escalation -- access another user's resources by manipulating user ID | [specific endpoint] | Modify resource ID in request | HIGH |
-
low Risky intent
intent-offensive-securitySKILL.md:2Offensive-security / dual-use content (legitimate for authorised testing; review intended use)name: security-pentest-planner
-
low Risky intent
intent-offensive-securitySKILL.md:3Offensive-security / dual-use content (legitimate for authorised testing; review intended use)description: Plans security penetration tests for web applications. Analyzes codebase, API routes, auth implementation, and infrastructure config to generate comprehensive pentest plans. For authorize
-
low Risky intent
intent-offensive-securitySKILL.md:8Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Security Penetration Test Planner
-
low Risky intent
intent-offensive-securitySKILL.md:10Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)Act as a senior application security engineer. Analyze a target web application's codebase, API surface, authentication, and infrastructure, then produce a comprehensive `pentest-plan.md` tailored to
quoted -
low Risky intent
intent-offensive-securitySKILL.md:16Offensive-security / dual-use content (legitimate for authorised testing; review intended use)> This penetration test plan is produced for authorized security assessments only. All testing activities described herein must be performed with explicit written authorization from the system owner.
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
frontmatter-keyunknown frontmatter key "tools"
Process rating: all ten parameters 53/100
- 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
- 20When it triggers. No condition that starts the skill
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 13 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 901 tokens
- 100Running it twice. No mutating operations
- 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
- +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
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 202: enough signal without eating the budget
- +4Structure: 5 headings
- +3Step-by-step instructions: 13 items
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.