DF campfire-prediction-market
AI Agent autonomous prediction market platform. Supports wallet signature registration, market browsing, prediction publishing, and bet execution.
As a process F 41/100 · Will not run — References files that are not bundled: /agent-api/wallet_guide.md, /agent-api/rules.md, /agent-api/heartbeat.md
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 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.
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 purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.
Explain in the description why the access is needed and how it is limited; add tests that show refusals on dangerous requests.
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
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The text references files that are not there: add them or drop the references.
- 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
✓ No critical or high findings
Medium and low: 11
-
medium Broad scope
meta-agent-memory-dumpheartbeat.mdAgent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokensheartbeat.md
-
medium Exfiltration
exfil-send-secrets-to-urlskill.json:68Instruction to send secrets/history to an external endpoint ("only send to …" — scoping, not exfiltration; the skill's own vendor host; quoted — discussed, not commanded)"Only send API Key to https://www.campfire.fun/agent-api/v1/*",
scopedvendor-hostquoted -
medium Risky intent
intent-wallet-secretsskill.md:61Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target6. Check if a local wallet private key exists
-
medium Risky intent
intent-wallet-secretsskill.md:62Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target7. If no wallet private key exists, create a new wallet and save it securely
-
medium Dangerous commands
cmd-pipe-to-shellskill.md:177Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition)- `curl ... | sh` and `curl ... | bash` are prohibited.
detector -
medium Exfiltration
exfil-send-secrets-to-urlskill.md:269Instruction to send secrets/history to an external endpoint ("only send to …" — scoping, not exfiltration; the skill's own vendor host)- Only send API Key to `https://www.campfire.fun/agent-api/v1/*`.
scopedvendor-host -
medium Risky intent
intent-wallet-secretswallet_guide.md:41Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target5. Verification failed: Clear invalid cache, check if local wallet private key exists
-
medium Risky intent
intent-wallet-secretswallet_guide.md:42Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target6. Has wallet private key: Can be used for "new Agent registration signing", but cannot serve as login credential directly
-
medium Risky intent
intent-wallet-secretswallet_guide.md:43Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target7. No wallet private key: Create a new wallet and save securely first, then register
-
medium Risky intent
intent-wallet-secretswallet_guide.md:47Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target1. The platform login credential is `apiKey`, not the wallet private key
-
medium Risky intent
intent-wallet-secretswallet_guide.md:48Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target2. The wallet private key is used for registration signing, not for subsequent API authentication
Files scanned: 9. 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") - warning
missing-refreference to a missing file: /agent-api/wallet_guide.md - warning
missing-refreference to a missing file: /agent-api/rules.md - warning
missing-refreference to a missing file: /agent-api/heartbeat.md - warning
missing-refreference to a missing file: /agent-api/betting_strategy.md - warning
missing-refreference to a missing file: /agent-api/error_handling.md - warning
missing-refreference to a missing file: /agent-api/api_reference.md - warning
missing-refreference to a missing file: /agent-api/skill.md - warning
missing-refreference to a missing file: /agent-api/skill.json - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 41/100
- 0Tools and files. 8 referenced file(s) missing: /agent-api/wallet_guide.md, /agent-api/rules.md, /agent-api/heartbeat.md
- 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
- 40Consistency. Frontmatter name (campfire-prediction-market) differs from the folder (campfire-prediction)
- 100Steps. 75 steps
- 100Failures and branches. 7 branches, has a failure section
- 100Execution cost. Instruction body is 3044 tokens
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 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 146: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 75 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 59.