FD founderclaw
FounderClaw — Multi-agent engineering team for OpenClaw. 29 skills, 6 agents (CEO + 5 departments), structured workspace, auto mode, vision sub-agent routing. Build startups with AI agents.
As a process D 43/100 · 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 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 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.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 11
-
high Exfiltration
intent-browser-credential-storedocs/founderclaw-mindmap.html:274Accesses a browser credential / cookie store<div class="files">qa, browse, cookies, chrome</div>
-
high Exfiltration
intent-browser-credential-storeSKILL.md:43Accesses a browser credential / cookie storeTesting: qa, qa-only, browse, setup-browser-cookies, connect-chrome
-
high Exfiltration
intent-browser-credential-storeTODOS.md:23Accesses a browser credential / cookie store**Why:** Right now, headed mode launches a fresh Chromium profile. Users must log in manually or import cookies. Chrome DevTools MCP connects to the user's actual Chrome ... instant access to every au
Medium and low: 8
-
medium Exfiltration
intent-browser-credential-storeARCHITECTURE.md:9Accesses a browser credential / cookie store (quoted — discussed, not commanded)The key insight: an AI agent interacting with a browser needs **sub-second latency** and **persistent state**. If every command cold-starts a browser, you're waiting 3-5 seconds per tool call. If the
quoted -
medium Dangerous commands
cmd-pipe-to-shell-known-hostdocs/index.html:68Pipe-to-shell installer from a well-known host (still executes remote code)Run this in terminal: <code>curl -fsSL https://raw.githubusercontent.com/ashish797/FounderClaw/main/install.sh | bash</code>
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostdocs/index.html:83Pipe-to-shell installer from a well-known host (still executes remote code)<code>curl -fsSL https://raw.githubusercontent.com/ashish797/FounderClaw/main/install.sh | bash</code>
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostdocs/index.html:136Pipe-to-shell installer from a well-known host (still executes remote code)Run this in terminal: curl -fsSL https://raw.githubusercontent.com/ashish797/FounderClaw/main/install.sh | bash
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostdocs/landing.html:68Pipe-to-shell installer from a well-known host (still executes remote code)<code>curl -fsSL https://raw.githubusercontent.com/ashish797/FounderClaw/main/install.sh | bash</code>
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostREADME.md:44Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://raw.githubusercontent.com/ashish797/FounderClaw/main/install.sh | bash
-
low Exfiltration
read-dotenvCONTRIBUTING.md:115Reads a .env file# 1. Copy .env.example and add your API key
-
low Exfiltration
read-dotenvCONTRIBUTING.md:116Reads a .env filecp .env.example .env
Files scanned: 40. 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")
Process rating: all ten parameters 43/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 4 mutating operations with no state check
- 60Tools and files. Uses tools (git) that frontmatter does not declare
- 100Steps. 6 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 365 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
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +3Description length 189: enough signal without eating the budget
- +4Structure: 5 headings
- +3Step-by-step instructions: 6 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.