Caveat verdict
campfire-prediction-market
campfire-agent
Reads local files AND makes external network calls
Skill instructs the agent to autonomously create EVM wallet private keys, persist them to disk, sign registration requests, and execute real prediction market bets — autonomous financial transactions and key management without explicit per-transaction user approval.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
What it does
These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Reads local files AND makes external network calls — the capabilities for data exfiltration co-occur (data-flow not verified)
LLM02 · LLM06 · ASI03
Reads files, encodes data, AND makes external network calls — the obfuscated-exfiltration pattern (data-flow not verified)
LLM02 · ASI03
Permission integrity
network_out
file_read
Findings (6)
Possible hardcoded credential
SKILL.md · code · API_KEY="替换为注册响应中的 data.apiKey
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
SKILL.md · prose · downgraded · curl ... | sh
Pipe to bash — executes piped content as shell commands
SKILL.md · prose · downgraded · | bash
Pipe to sh — executes piped content as shell commands
SKILL.md · prose · downgraded · | sh
Python os.environ.get — reads environment variable
SKILL.md · code · os.environ.get(
Python os.getenv — reads environment variable
wallet_guide.md · code · os.getenv(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
network_outfile_readcredential_accessdata_encoding Thanks — recorded.