BC openclaw-memory-stack
Total recall, 90% fewer tokens. Open source OpenClaw memory plugin — 5-engine local search, structured fact extraction, smart dedup, cross-agent sharing, and self-healing. Replace native memory with something that actually remembers. No cloud API, no subscription, MIT licensed and free.
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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.
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
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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
✓ No critical or high findings
Medium and low: 7
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostinstall.sh:428Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://bun.sh/install | bash 2>/dev/null
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostinstall.sh:450Pipe-to-shell installer from a well-known host (still executes remote code)curl -LsSf https://astral.sh/uv/install.sh | sh 2>/dev/null
-
medium Dangerous commands
cmd-shell-rcinstall.sh:562Writes to a shell startup fileecho " Add to your shell profile (~/.zshrc or ~/.bashrc):"
-
medium Exfiltration
intent-browser-credential-storeplugin/lib/state-io.mjs:1Accesses a browser credential / cookie store (code comment)// Pure filesystem operations for reading/writing local state files.
comment -
low Dangerous commands
cmd-background-processinstall.sh:339Starts a background / autostarted processdisown
-
low Dangerous commands
cmd-pipe-to-shell-known-hostinstall.sh:518Pipe-to-shell installer from a well-known host (still executes remote code) (string literal in code, not executed)warn " retry manually: curl -fsSL https://bun.sh/install | bash"
code literal -
low Dangerous commands
cmd-background-processinstall.sh:751Starts a background / autostarted processdisown
Files scanned: 32. 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")
Process rating: all ten parameters 53/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 6 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 16 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2585 tokens
- 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
- +2Single-language instructions
- +3Description length 287: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 16 items
- +4Has examples (6 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.