CC scan-skill
Deep security analysis of an individual skill before installation
Deep security analysis of an individual skill before installation
As a process C 62/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, failures and branches
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
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.
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.
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.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- 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 · 7
-
high Exfiltration
exfil-post-credential-filescripts/patterns.py:479Uploads a credential/secret file to a remote endpoint (detector / deny-list definition)pattern=r"curl\s+[^\n]*(-d|--data)\s+[^\n]*(cat|<)\s+[^\n]*(\.ssh|\.aws|\.gnupg|\.kube|\.env|credentials|id_rsa|private)",
detector
Medium and low: 6
-
medium Exfiltration
exfil-read-secret-filesscripts/patterns.py:507Reads credential / secret files (detector / deny-list definition)pattern=r"(cat|head|tail|less|more|type)\s+[^\n]*(\.ssh/id_rsa|\.aws/credentials|\.gnupg/|\.kube/config|/etc/shadow|/etc/passwd)",
detector -
medium Instruction override
en-ignore-previousscripts/patterns.py:577Instruction-override phrase ("ignore previous instructions") (detector / deny-list definition)description="Instruction override attempt -- trying to bypass system prompt",
detector -
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Read Glob Grep Bash
-
low Dangerous commands
cmd-pipe-to-shellscripts/patterns.py:65Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; string literal in code, not executed)pattern=r"<!--[\s\S]*?(curl|wget|bash|sh|exec|eval|system|python|node|perl)[\s\S]*?-->",
detectorcode literal -
low Dangerous commands
cmd-privilegescripts/patterns.py:645Privilege escalation / world-writable permissions (detector / deny-list definition; string literal in code, not executed)description="chmod 777 -- world-readable/writable/executable, overly permissive",
detectorcode literal
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 3. 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 62/100
- 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
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 11 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 380 tokens
- 100Running it twice. No mutating operations
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)
- +3Description length 65: 120–800 characters recommended
- -31 of 2 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 5 headings
- +3Step-by-step instructions: 11 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.