BC security
Enterprise-grade security framework for LobsterAI with audit logging, RBAC, input validation, output sanitization, code scanning, and dependency vulnerability detection.
As a process C 57/100 · Has gaps — weak spots: when it triggers, failures and branches, 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.
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 Dangerous commands
cmd-destructive-fsTECHNICAL_DOCUMENTATION.md:93Destructive filesystem command (wipes root/home/drive) (documentation table row; documentation of a security skill)| 系统破坏 | `rm -rf /`, `:(){:|:&};:` | 🔴 高危 |tablesecurity skill -
low Dangerous commands
cmd-privilegeDEPLOYMENT.md:141Privilege escalation / world-writable permissions (documentation of a security skill)# chown -R root:root security # 需要 sudo（不推荐）
security skill -
low Dangerous commands
cmd-persistenceinput_validator.py:310Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition; string literal in code, not executed)r'@reboot',
detectorcode literal -
low Dangerous commands
cmd-privilegeTECHNICAL_DOCUMENTATION.md:95Privilege escalation / world-writable permissions (documentation table row; documentation of a security skill)| 权限提升 | `sudo`, `su -`, `chmod 777` | 🔴 高危 |
tablesecurity skill
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 20. 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") - note
frontmatter-keyunknown frontmatter key "priority" - note
frontmatter-keyunknown frontmatter key "environment"
Process rating: all ten parameters 57/100
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 40Consistency. Frontmatter name (security) differs from the folder (lobsterai-security)
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 25 steps
- 100Execution cost. Instruction body is 957 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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)
- -31 of 1 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 169: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 25 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.