CD agent-messenger
Send batch messages to OpenClaw agents across Telegram, Discord, or other channels with delivery tracking and retry logic. Use when: (1) Broadcasting messages to multiple agents simultaneously, (2) Need delivery confirmation/ACK, (3) Want to trigger agent workflows via messages, (4) Require scheduled or triggered message campaigns. Supports templating, conditional routing, and fallback delivery.
As a process D 48/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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 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
- 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.
- 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 · 12
-
high Dangerous commands
cmd-persistencescripts/install_heartbeat_cron.sh:34Persistence mechanism (cron / launchd / scheduled task / autorun registry)(crontab -l 2>/dev/null; echo "$CRON_JOB") | crontab -
Medium and low: 11
-
medium Dangerous commands
cmd-persistencescripts/install_heartbeat_cron.sh:26Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition)crontab -l | grep -v "heartbeat_check.sh" | crontab -
detector -
medium Exfiltration
net-credential-usescripts/send_agent_msg.sh:100Credential used in a network call (verify the destination is the intended service)RESPONSE=$(curl -s -X POST "${TELEGRAM_API}${BOT_TOKEN}/sendMessage" \ -
low Dangerous commands
cmd-cron-mentionscripts/install_heartbeat_cron.sh:17Mentions editing / listing crontabif crontab -l 2>/dev/null | grep -q "heartbeat_check.sh"; then
-
low Dangerous commands
cmd-cron-mentionscripts/install_heartbeat_cron.sh:21Mentions editing / listing crontabcrontab -l | grep heartbeat
-
low Dangerous commands
cmd-cron-mentionscripts/install_heartbeat_cron.sh:26Mentions editing / listing crontabcrontab -l | grep -v "heartbeat_check.sh" | crontab -
-
low Dangerous commands
cmd-cron-mentionscripts/install_heartbeat_cron.sh:34Mentions editing / listing crontab(crontab -l 2>/dev/null; echo "$CRON_JOB") | crontab -
-
low Dangerous commands
cmd-cron-mentionscripts/install_heartbeat_cron.sh:39Mentions editing / listing crontab (string literal in code, not executed)echo " crontab -l"
code literal -
low Exfiltration
exfil-webhook-urlscripts/send_agent_msg.sh:8Webhook / callback URL commonly used for exfiltration (verify the destination) (the skill's own vendor host; quoted — discussed, not commanded)TELEGRAM_API="https://api.telegram.org/bot"
vendor-hostquoted -
low Exfiltration
exfil-webhook-urlscripts/send_telegram_direct.py:13Webhook / callback URL commonly used for exfiltration (verify the destination) (the skill's own vendor host; quoted — discussed, not commanded)TELEGRAM_API = "https://api.telegram.org/bot"
vendor-hostquoted -
low Dangerous commands
cmd-cron-mentionSKILL.md:35Mentions editing / listing crontabcrontab -l
-
low Exfiltration
exfil-webhook-urlSKILL.md:51Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)curl -X POST "https://api.telegram.org/bot<TOKEN>/sendMessage" \
placeholder
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Send batch messages to OpenClaw agents across Telegram, Discord, o… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 48/100
- 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. 13 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 7 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 559 tokens
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 398: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 7 items
- +4Has examples (6 code blocks)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.