BD 🛡️ AgentShield Audit
✅ Zero data leaves your system ✅ 52+ tests run locally in your agent ✅ Only certificate public key is shared ✅ Open source - verify every test
✅ Zero data leaves your system ✅ 52+ tests run locally in your agent ✅ Only certificate public key is shared ✅ Open source - verify every test
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 3
✓ No critical or high findings
Medium and low: 3
-
low Risky intent
intent-offensive-securityCHANGELOG.md:266Offensive-security / dual-use content (legitimate for authorised testing; review intended use)**Bug Bounty:** See [SECURITY.md](./SECURITY.md#bug-bounty)
-
low Risky intent
intent-offensive-securitySECURITY.md:170Offensive-security / dual-use content (legitimate for authorised testing; review intended use)### Bug Bounty
-
low Risky intent
intent-offensive-securitySKILL.md:160Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Privilege escalation attempts
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
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. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (🛡️ AgentShield Audit) differs from the folder (agentshield-audit)
- 100Tools and files. No external tools needed
- 100Steps. 77 steps
- 100Execution cost. Instruction body is 2641 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 16 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
- -272 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 142: enough signal without eating the budget
- +4Structure: 37 headings
- +3Step-by-step instructions: 77 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (1 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.