CF agent-security-scanner
AI Agent 安全扫描器 - 多语言检测 + AST 分析 + 意图识别 + LLM 验证
As a process F 35/100 · Will not run — References files that are not bundled: LICENSE
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 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
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The text references files that are not there: add them or drop the references.
- 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 · 10
✓ No critical or high findings
Medium and low: 10
-
medium Dangerous commands
cmd-persistencesrc/engine/smart_pattern_detector.py:34Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)"/etc/profile.d": 10, ".bashrc": 8, "Register-ScheduledTask": 12,
code literal -
medium Exfiltration
net-redirectable-api-keysrc/llm_analyzer.py:26Helper 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
-
medium Dangerous commands
cmd-destructive-fssrc/multi_language_scanner_v4.py:474Destructive filesystem command (wipes root/home/drive) (string literal in code, not executed; documentation of a security skill)(':(){ :|:& };:', 'fork_bomb_classic', 50),code literalsecurity skill -
low Dangerous commands
cmd-background-processRELEASE_NOTES.md:109Starts a background / autostarted process (documentation of a security skill)nohup python3 lingshun_scanner_daemon.py > logs/daemon.log 2>&1 &
security skill -
low Dangerous commands
cmd-background-processSKILL.md:82Starts a background / autostarted process (documentation of a security skill)nohup python3 lingshun_scanner_daemon.py > logs/daemon.log 2>&1 &
security skill -
low Dangerous commands
cmd-background-processSKILL.md:195Starts a background / autostarted process (documentation of a security skill)nohup python3 lingshun_scanner_daemon.py > logs/daemon.log 2>&1 &
security skill -
low Dangerous commands
cmd-privilegesrc/engine/smart_pattern_detector.py:27Privilege escalation / world-writable permissions (string literal in code, not executed)"os.setuid(": 20, "os.setgid(": 15, "os.chmod 0": 15,code literal -
low Dangerous commands
cmd-privilegesrc/engine/smart_pattern_detector.py:28Privilege escalation / world-writable permissions (string literal in code, not executed)"chmod +s": 20, "sudoers": 10, "setuid": 10, "setgid": 10,
code literal -
low Dangerous commands
cmd-background-processsrc/engine/smart_pattern_detector.py:32Starts a background / autostarted process (string literal in code, not executed)"crontab": 10, "/etc/cron": 10, "systemctl enable": 10, "systemctl start": 8,
code literal
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 26. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: LICENSE - note
frontmatter-keyunknown frontmatter key "repository" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "bugs"
Process rating: all ten parameters 35/100
- 0Tools and files. 1 referenced file(s) missing: LICENSE
- 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
- 100Steps. 14 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1386 tokens
- 100Running it twice. No mutating operations
- low 15 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)
- +3Description length 47: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -231 emoji in the instructions: noise for the model
- +2Single-language instructions
- +4Structure: 30 headings
- +3Step-by-step instructions: 14 items
- +4Has examples (14 code blocks)
- +4Reference files are cited in the instructions (2 of 5)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 63.