CD clawsec-suite
ClawSec suite manager with embedded advisory-feed monitoring, cryptographic signature verification, approval-gated malicious-skill response, and guided setup for additional security skills.
ClawSec suite manager with embedded advisory-feed monitoring, cryptographic signature verification, approval-gated malicious-skill response, and guided setup…
As a process D 41/100 · Unfinished process — References files that are not bundled: ../../wiki/exploitability-scoring.md
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.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
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
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:95High-entropy token-like string (may be an id, hash or a credential)MCow…XJX+GYGv…m6A=
Files scanned: 25. 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") - warning
missing-refreference to a missing file: ../../wiki/exploitability-scoring.md - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "clawdis" - note
edit-residuethe text marks something as outdated (lines 168): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 41/100
- 0Tools and files. 1 referenced file(s) missing: ../../wiki/exploitability-scoring.md
- 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. 5 mutating operations with no state check
- 70Execution cost. Instruction body is 4128 tokens
- 100Steps. 76 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 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
- -34 of 8 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 189: enough signal without eating the budget
- +4Structure: 27 headings
- +3Step-by-step instructions: 76 items
- +4Has examples (13 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.
In the sandbox The scripts kept to themselves
The skill's scripts were run in a throwaway machine: no network, fake keys in the home directory, a tracer watching. We wrote down what they did. Reaching for the network or for secrets caps the technical grade at C; a quiet run adds no points.
Запущено 12 скриптов, ещё 6 не поместились в лимит; каждому дали двадцать секунд, поддельный домашний каталог с ключами и сеть, в которой ничего нет.
scripts/discover_skill_catalog.mjs | ничего за пределами своей папки |
scripts/generate_checksums_json.mjs | ничего за пределами своей папки |
scripts/guarded_skill_install.mjs | ничего за пределами своей папки |
scripts/local_file_io.mjs | ничего за пределами своей папки |
scripts/setup_advisory_cron.mjs | ничего за пределами своей папки |
scripts/setup_advisory_hook.mjs | ничего за пределами своей папки |
scripts/sign_detached_ed25519.mjs | ничего за пределами своей папки |
scripts/verify_detached_ed25519.mjs | ничего за пределами своей папки |
hooks/clawsec-advisory-guardian/handler.ts | ничего за пределами своей папки |
hooks/clawsec-advisory-guardian/lib/advisory_scope.mjs | ничего за пределами своей папки |
hooks/clawsec-advisory-guardian/lib/feed.mjs | ничего за пределами своей папки |
hooks/clawsec-advisory-guardian/lib/local_file_io.mjs | ничего за пределами своей папки |
21 Oct 2026