BC self-smarter-everyday
Autonomous daily self-improvement system for AI agents. Runs nightly self-reflection, self-audit, memory compaction, prompt evolution, and skill gap analysis at 2AM. Agent automatically gets smarter every day through structured introspection and continuous learning loops.
Autonomous daily self-improvement system for AI agents.
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
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
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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
-
high Dangerous commands
cmd-persistencescripts/setup.sh:154Persistence mechanism (cron / launchd / scheduled task / autorun registry)(crontab -l 2>/dev/null; echo "${CRON_SCHEDULE} ${CRON_CMD}") | crontab -
Medium and low: 9
-
medium Exfiltration
intent-browser-credential-storeskill-card.md:17Accesses a browser credential / cookie store (documentation of a security skill)Developers and agent operators use this skill to configure an OpenClaw agent for scheduled self-review, local state maintenance, prompt variant tracking, memory lifecycle management, and daily improve
security skill -
low Dangerous commands
cmd-cron-mentionscripts/setup.sh:150Mentions editing / listing crontabif crontab -l 2>/dev/null | grep -q "nightly_routine.py"; then
-
low Dangerous commands
cmd-cron-mentionscripts/setup.sh:154Mentions editing / listing crontab(crontab -l 2>/dev/null; echo "${CRON_SCHEDULE} ${CRON_CMD}") | crontab - -
low Dangerous commands
cmd-privilegeSECURITY.md:73Privilege escalation / world-writable permissions (negated — the text forbids it)- **NO privilege escalation:** Scripts run with user-level permissions only. No `sudo`, no `setuid`.
negated -
low Risky intent
intent-offensive-securitySECURITY.md:73Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **NO privilege escalation:** Scripts run with user-level permissions only. No `sudo`, no `setuid`.
-
low Risky intent
intent-offensive-securitySECURITY.md:213Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Privilege escalation (scripts gaining more access than intended).
-
low Instruction override
en-ignore-previousSKILL.md:213Instruction-override phrase ("ignore previous instructions") (negated — the text forbids it)2. **Never Modify Safety Boundaries** — Safety rules are immutable. Self-improvement cannot override safety constraints.
negated
A further 2 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 40. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5771 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 52/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 10 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70Execution cost. Instruction body is 5771 tokens
- 100Steps. 164 steps
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 19 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
- +3Output format is not stated: the model decides each time
- -222 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 272: enough signal without eating the budget
- +4Structure: 42 headings
- +3Step-by-step instructions: 164 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (10 of 10)
- +3All 5 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.