CF soul-memory
Intelligent memory management system v3.5.13 - 修復 heartbeat-trigger.py 改用上次 heartbeat 到現在的增量窗口抓取 important context，避免固定 3 小時窗口遺漏與重掃。
As a process F 38/100 · Will not run — References files that are not bundled: LICENSE
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 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.
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 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 · 7
-
high Dangerous commands
cmd-persistenceinstall.sh:494Persistence mechanism (cron / launchd / scheduled task / autorun registry)(crontab -l 2>/dev/null | grep -v "soul_memory" ; cat "$CRON_TMP") | crontab -
Medium and low: 6
-
medium Broad scope
meta-agent-memory-dumpHEARTBEAT.mdAgent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokensHEARTBEAT.md
-
medium Dangerous commands
cmd-shell-rcinstall.sh:871Writes to a shell startup fileecho -e " ${YELLOW}source ~/.bashrc${NC} (或 ~/.zshrc)" -
low Dangerous commands
cmd-cron-mentioninstall.sh:484Mentions editing / listing crontabif crontab -l 2>/dev/null | grep -q "soul_memory"; then
-
low Dangerous commands
cmd-cron-mentioninstall.sh:494Mentions editing / listing crontab(crontab -l 2>/dev/null | grep -v "soul_memory" ; cat "$CRON_TMP") | crontab -
-
low Dangerous commands
cmd-cron-mentioninstall.sh:501Mentions editing / listing crontabcrontab -l | grep "soul_memory"
-
low Dangerous commands
cmd-cron-mentioninstall.sh:881Mentions editing / listing crontab (detector / deny-list definition; string literal in code, not executed)echo -e " ${YELLOW}crontab -l | grep soul_memory${NC}"detectorcode literal
Files scanned: 68. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: LICENSE - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "repository" - note
frontmatter-keyunknown frontmatter key "keywords"
Process rating: all ten parameters 38/100
- 0Tools and files. 1 referenced file(s) missing: LICENSE
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 100Steps. 58 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2054 tokens
- low 15 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
- -229 emoji in the instructions: noise for the model
- +2Single-language instructions
- +3Description length 132: enough signal without eating the budget
- +4Structure: 31 headings
- +3Step-by-step instructions: 58 items
- +4Has examples (8 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.