SKILLEMALL.ai

BD skill-security-protocol

Teach your AI agent to think about security. A reasoning methodology for vetting skills before installation — red/green flag heuristics, 4-phase audit protocol, post-install verification. No scripts, no dependencies. Just judgment. Built on fallibilism (being wrong about a skill's safety is recoverable; being overconfident is not) and relational security (you and your human decide together on edge cases — trust is built through transparency, not just detection).

modbender/skill-library-mcp Agent Skills author: modbender MIT 1 file body ≈ 4 537 tokens Open the sourcegithub.com analyzed 2 d ago

Teach your AI agent to think about security.

As a process D 35/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerSoftware developmentAI and agentsSecuritytype and topics are labelled automatically from the skill text
JSON
Technical rating
B
82/100
safety, quality, tests
Safety 60%
92
Quality 40%
66
Run on models
none yet
Process rating
D
35/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

How to improve

  1. 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 · 8

✓ No critical or high findings

Medium and low: 8
  • low Dangerous commands cmd-privilege SKILL.md:106
    Privilege escalation / world-writable permissions (documentation table row; documentation of a security skill)
    | **Requests for elevated permissions** | Unnecessary privilege escalation | `sudo`, `chmod 777`, SUID bits |
    tablesecurity skill
  • low Risky intent intent-offensive-security SKILL.md:106
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | **Requests for elevated permissions** | Unnecessary privilege escalation | `sudo`, `chmod 777`, SUID bits |
  • low Risky intent intent-offensive-security SKILL.md:109
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | **Credential harvesting** | Stealing tokens, keys, passwords | Reading `~/.ssh/`, `~/.aws/`, env vars |
  • low Dangerous commands cmd-cron-mention SKILL.md:188
    Mentions editing / listing crontab (documentation of a security skill)
    crontab -l
    security skill
  • low Dangerous commands cmd-cron-mention SKILL.md:334
    Mentions editing / listing crontab (documentation of a security skill)
    crontab -l
    security skill

A further 3 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • note frontmatter-key unknown frontmatter key "homepage"
  • note frontmatter-key unknown frontmatter key "emoji"

Process rating: all ten parameters 35/100

  • 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
  • 30Running it twice. 7 mutating operations with no state check
  • 40Consistency. Frontmatter name (skill-security-protocol) differs from the folder (nyx-archive-skill-security-protocol)
  • 60Tools and files. Uses tools (bash, web, git) that frontmatter does not declare
  • 70Execution cost. Instruction body is 4537 tokens
  • 85Steps. 67 steps, 2 vague phrases
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 15 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (3 tags): a typed call is more reliable

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
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • +1No license
  • +2Single-language instructions
  • +3Description length 466: enough signal without eating the budget
  • +4Structure: 46 headings
  • +3Step-by-step instructions: 67 items
  • +4Has examples (7 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.