BC skill-security-check
Scan a third-party Claude Code skill for security risks before enabling it. Use when user wants to audit, check, or verify the safety of a skill.
As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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 contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
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
- 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 · 11
✓ No critical or high findings
Medium and low: 11
-
medium Dangerous commands
cmd-pipe-to-shellREADME_EN.md:131Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)| Remote code execution | Scripts contain curl \| bash pattern | CRITICAL |
security skill -
medium Dangerous commands
cmd-pipe-to-shellREADME.md:132Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)| 远程代码执行 | 脚本中 curl \| bash 模式 | CRITICAL |
security skill -
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Read Grep Glob Bash
-
low Dangerous commands
cmd-privilegeinstall.sh:79Privilege escalation / world-writable permissions (string literal in code, not executed)- **Destructive commands**: `rm -rf`, `rm -f`, `chmod 777`, `mkfs`, `dd if=`
code literal -
low Dangerous commands
cmd-privilegeinstall.sh:217Privilege escalation / world-writable permissions (detector / deny-list definition; string literal in code, not executed)if grep -rn -E 'rm -rf|rm -f |chmod 777|mkfs|dd if=|:\(\)\{|fork bomb' "$SKILL_DIR" 2>/dev/null; thendetectorcode literal -
low Dangerous commands
cmd-privilegeREADME_EN.md:146Privilege escalation / world-writable permissions (documentation of a security skill)| Destructive commands | rm -rf, chmod 777, mkfs, dd, fork bomb |
security skill -
low Risky intent
intent-offensive-securityREADME_EN.md:148Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Privilege escalation | sudo, su, chown, chmod |
-
low Dangerous commands
cmd-privilegeREADME.md:147Privilege escalation / world-writable permissions (documentation of a security skill)| 破坏性命令 | rm -rf, chmod 777, mkfs, dd, fork bomb |
security skill -
low Risky intent
intent-offensive-securitySKILL.md:58Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **Privilege escalation**: `sudo`, `su`, `chown`
A further 2 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 7. 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
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (skill-security-check) differs from the folder (skills-security-check)
- 65Failures and branches. 3 branches
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 22 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 1050 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
- -213 emoji in the instructions: noise for the model
- -31 of 2 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 145: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 22 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.