BC pipedream-connect
Connect OpenClaw agents to thousands of apps via Pipedream Connect with per-agent OAuth isolation, first-class MCP tool exposure, live connected-account discovery, and dynamic full-catalog browsing. Use when setting up or maintaining the OpenClaw Pipedream integration, troubleshooting agent app connections, documenting the Pipedream dashboard / agent tools flow, or working on Pipedream catalog, icons, activation, and MCP tool registration behavior.
As a process C 51/100 · Has gaps — 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.
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 · 8
-
high Dangerous commands
cmd-persistencescripts/setup-cron.sh:34Persistence mechanism (cron / launchd / scheduled task / autorun registry)(crontab -l 2>/dev/null || echo "") | { cat; echo "$CRON_LINE"; } | crontab -
Medium and low: 7
-
low Exfiltration
exfil-webhook-urlreference/pipedream-backend.ts:339Webhook / callback URL commonly used for exfiltration (verify the destination) (the skill's own vendor host; quoted — discussed, not commanded)baseUrl: "https://remote.mcp.pipedream.net",
vendor-hostquoted -
low Exfiltration
exfil-webhook-urlreference/pipedream-controller.ts:216Webhook / callback URL commonly used for exfiltration (verify the destination) (the skill's own vendor host; quoted — discussed, not commanded)const response = await fetch("https://remote.mcp.pipedream.net", {vendor-hostquoted -
low Exfiltration
exfil-webhook-urlreference/pipedream-controller.ts:432Webhook / callback URL commonly used for exfiltration (verify the destination) (the skill's own vendor host; quoted — discussed, not commanded)const response = await fetch("https://remote.mcp.pipedream.net", {vendor-hostquoted -
low Dangerous commands
cmd-cron-mentionscripts/setup-cron.sh:28Mentions editing / listing crontabif crontab -l 2>/dev/null | grep -q "pipedream-token-refresh"; then
-
low Dangerous commands
cmd-cron-mentionscripts/setup-cron.sh:30Mentions editing / listing crontabcrontab -l | grep "pipedream-token-refresh"
-
low Dangerous commands
cmd-cron-mentionscripts/setup-cron.sh:34Mentions editing / listing crontab(crontab -l 2>/dev/null || echo "") | { cat; echo "$CRON_LINE"; } | crontab - -
low Dangerous commands
cmd-cron-mentionscripts/setup-cron.sh:47Mentions editing / listing crontab (string literal in code, not executed)echo " crontab -l"
code literal
Files scanned: 12. 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 51/100
- 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
- 85Steps. 71 steps, 1 vague phrases
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1627 tokens
- low 11 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
- -41 reference files, but SKILL.md never points to them: the model will not open them
- -32 of 2 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 452: enough signal without eating the budget
- +4Structure: 27 headings
- +3Step-by-step instructions: 71 items
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.