BD AI Agent Skill Scanner
Security scanner for AI agent skills. Detects hardcoded secrets, unsafe code execution, prompt injection, and malware patterns in under 50ms. Scan before you install.
Security scanner for AI agent skills.
As a process D 39/100 · 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 text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.
An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.
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 · 5
✓ No critical or high findings
Medium and low: 5
-
medium Instruction override
en-ignore-previoussignatures.json:114Instruction-override phrase ("ignore previous instructions") (detector / deny-list definition)"fragments": ["ignore previous instructions", "ignore the above", "ignore all instructions", "override instructions", "you are now"],
detector -
low Dangerous commands
cmd-pipe-to-shellscripts/vetter.py:103Downloads and executes remote code from an unrecognised host (pipe to shell) (code comment; documentation of a security skill)# Special handling for pipe-to-shell: only flag if curl/wget X | sh/bash pattern
commentsecurity skill -
low Dangerous commands
cmd-privilegesignatures.json:79Privilege escalation / world-writable permissions (detector / deny-list definition; string literal in code, not executed)"fragments": ["chmod 777", "chmod 666"],
detectorcode literal -
low Dangerous commands
cmd-pipe-to-shellSKILL.md:34Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation table row; documentation of a security skill)| Pipe to shell | Critical | `curl ... | bash` |
tablesecurity skill -
low Dangerous commands
cmd-privilegeSKILL.md:45Privilege escalation / world-writable permissions (documentation table row; documentation of a security skill)| Permission overrides | Medium | `chmod 777` |
tablesecurity skill
Files scanned: 11. 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 39/100
- 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. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (AI Agent Skill Scanner) differs from the folder (ai-agent-skill-scanner)
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 100Steps. 8 steps
- 100Execution cost. Instruction body is 525 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
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +2Single-language instructions
- +3Description length 166: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 8 items
- +4Has examples (3 code blocks)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.