DB calibre-ebooks
Manage and query the local Calibre library through the Books API, using local Calibre/RAG helpers only when file resolution or semantic indexing is explicitly needed.
As a process B 67/100 · Nearly there — weak spots: inputs and preconditions, execution cost
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.
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
- 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 · 19
✓ No critical or high findings
Medium and low: 19
-
medium Dangerous commands
cmd-privilegecalibre-openclaw-gateway/install_service.sh:315Privilege escalation / world-writable permissionssudo tee "$SERVICE_FILE" > /dev/null <<EOF
-
medium Dangerous commands
cmd-privilegecalibre-openclaw-gateway/install_service.sh:393Privilege escalation / world-writable permissionssudo tee "$NIGHTLY_SERVICE_FILE" > /dev/null <<EOF
-
medium Dangerous commands
cmd-privilegecalibre-openclaw-gateway/install_service.sh:424Privilege escalation / world-writable permissionssudo tee "$NIGHTLY_TIMER_FILE" > /dev/null <<EOF
-
medium Dangerous commands
cmd-privilegecalibre-openclaw-gateway/install_service.sh:527Privilege escalation / world-writable permissionssudo rm -f "$SERVICE_FILE"
-
medium Dangerous commands
cmd-privilegecalibre-openclaw-gateway/install_service.sh:533Privilege escalation / world-writable permissionssudo rm -f "$NIGHTLY_SERVICE_FILE"
-
medium Exfiltration
net-credential-usecalibre-openclaw-gateway/README.md:129Credential used in a network call (verify the destination is the intended service)curl -H "X-API-Key: $API_KEY" \
-
medium Exfiltration
net-credential-usecalibre-openclaw-gateway/README.md:234Credential used in a network call (verify the destination is the intended service)curl -H "X-API-Key: $API_KEY" \
-
medium Exfiltration
net-credential-usecalibre-openclaw-gateway/README.md:482Credential used in a network call (verify the destination is the intended service)curl -H "X-API-Key: $API_KEY" \
-
medium Exfiltration
net-credential-usecalibre-openclaw-gateway/README.md:486Credential used in a network call (verify the destination is the intended service)curl -H "X-API-Key: $API_KEY" \
-
medium Exfiltration
net-credential-usecalibre-openclaw-gateway/README.md:526Credential used in a network call (verify the destination is the intended service)curl -H "X-API-Key: $API_KEY" \
-
medium Broad scope
meta-agent-memory-dumprapport-bibliotecario-agent/HEARTBEAT.mdAgent memory / workspace files bundled with the skill (5) — likely a workspace dump with personal data or tokensrapport-bibliotecario-agent/HEARTBEAT.md, rapport-bibliotecario-agent/IDENTITY.md, rapport-bibliotecario-agent/MEMORY.md, rapport-bibliotecario-agent/SOUL.md, rapport-bibliotecario-agent/USER.md
-
medium Exfiltration
net-redirectable-api-keyscripts/books_api_client.py:100Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
low Exfiltration
read-dotenvcalibre-openclaw-gateway/install_service.sh:88Reads a .env file (quoted — discussed, not commanded)print_info " cp .env.example /path/to/.env"
quoted -
low Dangerous commands
cmd-background-processcalibre-openclaw-gateway/install_service.sh:468Starts a background / autostarted processsudo systemctl enable "$SERVICE_NAME"
-
low Dangerous commands
cmd-background-processcalibre-openclaw-gateway/install_service.sh:473Starts a background / autostarted processsudo systemctl enable --now "$NIGHTLY_SERVICE_NAME.timer"
-
low Dangerous commands
cmd-background-processcalibre-openclaw-gateway/install_service.sh:615Starts a background / autostarted processsudo systemctl enable "$SERVICE_NAME"
-
low Dangerous commands
cmd-background-processcalibre-openclaw-gateway/install_service.sh:616Starts a background / autostarted processsudo systemctl enable --now "$NIGHTLY_SERVICE_NAME.timer"
-
low Exfiltration
read-dotenvcalibre-openclaw-gateway/run.sh:85Reads a .env file (quoted — discussed, not commanded)echo " cp .env.example /path/to/.env"
quoted -
low Secrets in code
secret-high-entropy-tokenscripts/books_api_client.py:492High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)boundary = "----…0gW"
quoted
Files scanned: 55. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 8503 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 67/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Execution cost. Instruction body is 8503 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 160 steps
- 100Failures and branches. 26 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 16 top-level sections: this looks like several domains in one skill
- high The skill tells the model to perform an irreversible action with no human approval
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)
- +1No license
- +2Single-language instructions
- +3Description length 166: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 160 items
- +3Output format is stated explicitly
- +4Has examples (21 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.