CC openclaw-daily-backup
This skill should be used when the user asks for daily backup, scheduled backup, restore, rollback, recovery, or routine protection of core OpenClaw workspace identity/config files.
As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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 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.
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
- 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 · 19
✓ No critical or high findings
Medium and low: 19
-
medium Broad scope
meta-agent-memory-dumpbackups/2026-03-14T05-39-50/HEARTBEAT.mdAgent memory / workspace files bundled with the skill (8) — likely a workspace dump with personal data or tokensbackups/2026…-50/HEARTBEAT.md, backups/2026…-50/IDENTITY.md, backups/2026…-50/SOUL.md, backups/2026…-50/USER.md, backups/named/manu…212/HEARTB
-
medium Dangerous commands
cmd-pipe-to-shellFINAL-DELIVERY-REPORT.md:168Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)3. **用户体验差距:** ClawLite 的 "one-click install" (`curl | bash`) 与 DMG 下载流程不同
quoted -
medium Dangerous commands
cmd-pipe-to-shellFINAL-DELIVERY-REPORT.md:173Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)2. **简单:** 当前 `curl | bash` 方法 50 行 shell 脚本，DMG 方法需 500+ 行
quoted -
medium Dangerous commands
cmd-pipe-to-shellFINAL-DELIVERY-REPORT.md:178Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)- **主要分发:** 保持 `curl | bash` (开发者和 CLI 用户)
quoted -
medium Dangerous commands
cmd-pipe-to-shellFINAL-DELIVERY-REPORT.md:318Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)- **忽略用户反馈:** 先发布 `curl | bash`，根据反馈迭代
quoted -
low Secrets in code
secret-high-entropy-tokenDELIVERY_REPORT.md:96High-entropy token-like string (may be an id, hash or a credential)node scripts/restore.mjs --timestamp pre-…-00
-
low Dangerous commands
cmd-cron-mentionEXAMPLES.md:8Mentions editing / listing crontab (test fixture / example file)# Add to crontab: crontab -e
fixture -
low Dangerous commands
cmd-cron-mentionEXAMPLES.md:79Mentions editing / listing crontab (test fixture / example file)# Add to crontab: crontab -e
fixture -
low Secrets in code
secret-high-entropy-tokenEXAMPLES.md:102High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)node scripts/restore.mjs --timestamp pre-…-00
fixture -
low Dangerous commands
cmd-cron-mentionexamples/automated-backup.sh:3Mentions editing / listing crontab (code comment; test fixture / example file)# Add to crontab: crontab -e
commentfixture -
low Secrets in code
secret-high-entropy-tokenFINAL-DELIVERY-REPORT.md:43High-entropy token-like string (may be an id, hash or a credential)node scripts/restore.mjs --timestamp pre-…-00
-
low Secrets in code
secret-high-entropy-tokenP0-1-DELIVERY-REPORT.md:103High-entropy token-like string (may be an id, hash or a credential)node scripts/restore.mjs --timestamp pre-…-00
-
low Dangerous commands
cmd-cron-mentionP0-1-DELIVERY-REPORT.md:151Mentions editing / listing crontab# Add to crontab: crontab -e
-
low Secrets in code
secret-high-entropy-tokenREADME.md:121High-entropy token-like string (may be an id, hash or a credential)node scripts/restore.mjs --timestamp pre-…-00
-
low Dangerous commands
cmd-cron-mentionREADME.md:198Mentions editing / listing crontab# Add to crontab: crontab -e
-
low Secrets in code
secret-high-entropy-tokenRUNBOOK.md:105High-entropy token-like string (may be an id, hash or a credential)node scripts/restore.mjs --timestamp pre-…-00
-
low Dangerous commands
cmd-cron-mentionRUNBOOK.md:240Mentions editing / listing crontab# Add to crontab: crontab -e
-
low Dangerous commands
cmd-cron-mentionRUNBOOK.md:256Mentions editing / listing crontab# Add to crontab: crontab -e
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:152High-entropy token-like string (may be an id, hash or a credential)node scripts/restore.mjs --timestamp pre-…-00
Files scanned: 42. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 54/100
- 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. 8 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 42 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1708 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 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)
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +3Description length 181: enough signal without eating the budget
- +4Structure: 28 headings
- +3Step-by-step instructions: 42 items
- +4Has examples (14 code blocks)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.