BC lark-toolkit
Comprehensive Lark/Feishu API skill for OpenClaw agents. Covers all Lark operations via three access paths: claw-lark plugin (message tool), MCP tools (mcporter), and direct Open API (curl). Use when: (1) sending/receiving Lark messages, (2) managing groups or members, (3) listing department users or contacts, (4) creating calendar events, (5) working with docs/bitable/wiki/OKR/tasks, (6) setting up a new Lark bot, (7) debugging webhook/connection issues, (8) any Lark Open API operation the message tool or MCP doesn't support. Covers both Lark International (open.larksuite.com) and Feishu China (open.feishu.cn).
As a process C 56/100 · Has gaps — weak spots: result and completion, when it triggers, 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.
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
- 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-persistencereferences/troubleshooting.md:26Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)1. Kill competing process: `kill PID && launchctl unload ~/Library/LaunchAgents/com.xxx.plist`
quoted -
medium Exfiltration
net-credential-useSKILL.md:90Credential used in a network call (verify the destination is the intended service)curl -s -H "Authorization: Bearer $TOKEN" \
-
medium Exfiltration
net-credential-useSKILL.md:94Credential used in a network call (verify the destination is the intended service)curl -s -H "Authorization: Bearer $TOKEN" \
-
medium Exfiltration
net-credential-useSKILL.md:103Credential used in a network call (verify the destination is the intended service)curl -s -H "Authorization: Bearer $TOKEN" \
-
low Secrets in code
secret-high-entropy-tokenreferences/mcp-tools.md:16High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| `bita…ist` | List fields of a table |
table -
low Secrets in code
secret-high-entropy-tokenreferences/mcp-tools.md:18High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| `bita…ate` | Create record (row) in table |
table -
low Secrets in code
secret-high-entropy-tokenreferences/mcp-tools.md:19High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| `bita…rch` | Search records with filters |
table -
low Secrets in code
secret-high-entropy-tokenreferences/mcp-tools.md:20High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| `bita…ate` | Update existing record |
table -
low Secrets in code
secret-high-entropy-tokenreferences/mcp-tools.md:28High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| `cale…ate` | Create calendar event (summary, start/end time, attendees) |
table
Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 56/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 12 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 29 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1744 tokens
- low 10 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
- +1No license
- +2Single-language instructions
- +3Description length 619: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 29 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (6 of 6)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.