BF everything-search-breadmemory
基于 Everything/es.exe 的本地文件搜索引擎 + 面包屑知识管理系统 + 艾宾浩斯复习引擎 + 拓扑甜甜圈知识关联。
As a process F 33/100 · Will not run — References files that are not bundled: references/*.md
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.
- 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 · 4
✓ No critical or high findings
Medium and low: 4
-
medium Dangerous commands
cmd-persistencereferences/workflow.md:65Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation table row)| **Windows 任务计划** | `schtasks` 命令行或 GUI | `schtasks /create /tn "拓扑甜甜圈更新" /tr "python topology_donut.py generate" /sc daily /st 02:00` |
table -
medium Dangerous commands
cmd-persistencereferences/workflow.md:66Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation table row)| **macOS Launchd** | 创建 `.plist` 到 `~/Library/LaunchAgents/` | 配置 StartCalendarInterval 和 ProgramArguments |
table -
medium Dangerous commands
cmd-persistencescripts/topology_donut.py:734Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)schtasks /create /tn "拓扑甜甜圈更新" /tr "python topology_donut.py generate" /sc daily /st 02:00
code literal -
low Dangerous commands
cmd-cron-mentionreferences/workflow.md:64Mentions editing / listing crontab (documentation table row)| **Linux/macOS cron** | `crontab -e` 添加定时任务 | `0 2 * * * python3 ~/.workbuddy/skills/everything-search-breadmemory/scripts/topology_donut.py generate` |
table
Files scanned: 15. 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: references/*.md - note
frontmatter-keyunknown frontmatter key "trigger_negative" - note
frontmatter-keyunknown frontmatter key "external_data_dir" - note
frontmatter-keyunknown frontmatter key "sensitive_access" - note
frontmatter-keyunknown frontmatter key "critical_write" - note
frontmatter-keyunknown frontmatter key "permission_weight" - note
frontmatter-keyunknown frontmatter key "data_dir"
Process rating: all ten parameters 33/100
- 0Tools and files. 1 referenced file(s) missing: references/*.md
- 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
- 100Steps. 10 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 934 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)
- +3Description length 66: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Structure: 14 headings
- +3Step-by-step instructions: 10 items
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (7 of 8)
- +3All 4 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.