BC secondmind
Autonomous three-tier memory with proactive initiative, project tracking, and social intelligence. Ingests OpenClaw conversations, extracts knowledge + emotions, and proactively suggests automations, fixes, and project ideas. v1.4.0: Project tracking, semantic dedup, bulk feedback, archive retrieval, gentle reminders. All models via OpenRouter Cloud. Cross-platform: Linux + Windows.
As a process C 57/100 · 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 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 · 9
✓ No critical or high findings
Medium and low: 9
-
medium Dangerous commands
cmd-persistencesetup.js:95Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)if(t.d) execSync(`schtasks /Create /TN "${t.name}" /TR ${cmd} /SC DAILY /ST ${t.d} /F`);quoted -
medium Dangerous commands
cmd-persistencesetup.js:96Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)else execSync(`schtasks /Create /TN "${t.name}" /TR ${cmd} /SC MINUTE /MO ${t.m} /F`);quoted -
low Dangerous commands
cmd-cron-mentionAGENT-SETUP.md:32Mentions editing / listing crontabcrontab -l | grep secondmind
-
low Dangerous commands
cmd-background-processAGENT-SETUP.md:37Starts a background / autostarted processnohup node scripts/telegram-bot.js >> /tmp/secondmind-bot.log 2>&1 &
-
low Secrets in code
secret-high-entropy-tokenREADME.md:96High-entropy token-like string (may be an id, hash or a credential) (placeholder value)"apiKey": "sk-o…ERE"
placeholder -
low Dangerous commands
cmd-cron-mentionREADME.md:133Mentions editing / listing crontab# Add these to your crontab (crontab -e):
-
low Dangerous commands
cmd-background-processREADME.md:271Starts a background / autostarted processnohup node scripts/telegram-bot.js > /tmp/secondmind-bot.log 2>&1 &
-
low Dangerous commands
cmd-cron-mentionREADME.md:437Mentions editing / listing crontab (detector / deny-list definition; documentation table row)| Crons not running | `crontab -l | grep secondmind` – if empty, run `node setup.js` again |
detectortable -
low Dangerous commands
cmd-cron-mentionsetup.js:81Mentions editing / listing crontab (quoted — discussed, not commanded)let ex=''; try{ex=execSync('crontab -l 2>/dev/null',{encoding:'utf8'})}catch{}quoted
Files scanned: 27. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "emoji"
Process rating: all ten parameters 57/100
- 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. 14 mutating operations with no state check
- 60Tools and files. Uses tools (node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 85Steps. 43 steps, 1 vague phrases
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1619 tokens
- low The response is described with custom markup (4 tags): a typed call is more reliable
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
- -32 of 11 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 385: enough signal without eating the budget
- +4Structure: 23 headings
- +3Step-by-step instructions: 43 items
- +4Has examples (15 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.