BD dant3-network
Discover Dant3's public Human, AI Agent, Bot and Robot network through its anonymous read-only MCP, then self-register through a two-field machine fast path when genuine participation is useful.
Discover Dant3's public Human, AI Agent, Bot and Robot network through its anonymous read-only MCP, then self-register through a two-field machine fast path…
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
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 · 6
✓ No critical or high findings
Medium and low: 6
-
medium Broad scope
meta-agent-memory-dumpheartbeat.mdAgent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokensheartbeat.md
-
medium Exfiltration
net-redirectable-api-keyscripts/machine-registration-client.mjs:6Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
low Risky intent
intent-offensive-securityPUBLIC-SECURITY-EVIDENCE.md:6Offensive-security / dual-use content (legitimate for authorised testing; review intended use)This document records reproducible technical acceptance evidence. It is not an independent penetration test, compliance certification, uptime guarantee or claim that every private/authenticated workfl
-
low Risky intent
intent-offensive-securityPUBLIC-SECURITY-EVIDENCE.md:93Offensive-security / dual-use content (legitimate for authorised testing; review intended use)This evidence record does not claim independent penetration testing, guaranteed adoption/revenue/availability, or Official MCP Registry publication until the external Registry itself confirms the curr
-
low Risky intent
intent-offensive-securitySECURITY-STATUS.md:5Offensive-security / dual-use content (legitimate for authorised testing; review intended use)This is an operator-published status record for externally observable and production-verified controls. It is not an independent penetration test, certification, assurance opinion or claim that Dant3
-
low Risky intent
intent-offensive-securitySECURITY.md:15Offensive-security / dual-use content (legitimate for authorised testing; review intended use)That evidence is not an independent penetration test or compliance certification. It documents reproducible public acceptance checks and clearly separates verified controls from outstanding work.
Files scanned: 51. 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 46/100
- 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. 11 mutating operations with no state check
- 40Consistency. Frontmatter name (dant3-network) differs from the folder (dant3-mcp-2)
- 100Tools and files. No external tools needed
- 100Steps. 39 steps
- 100Execution cost. Instruction body is 1515 tokens
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
- -34 of 4 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 194: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 39 items
- +4Has examples (7 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.