Security audit
Security checks for vulnerabilities and agentic risk
This skill openly solves Moltbook verification math and can optionally submit the answer with a user-provided API key, with no hidden persistence or unrelated data access found.
Install this only if you intend your agent to solve Moltbook verification challenges. Use the submission feature only with an API key you are comfortable sending to Moltbook, and review Moltbook's rules before automating verification during posting.
The documented purpose emphasizes solving verification math locally, but the skill behavior also includes submitting answers over the network and accepting API keys for authenticated requests. This description-behavior mismatch is dangerous because it can mislead users and reviewers about the true trust boundary, causing them to provide credentials or install a skill with broader capabilities than expected.
The skill advertises and demonstrates network-capable behavior, including submitting verification answers to an external API, but does not declare any tool scope or permissions. This weakens security boundaries and reviewability because operators cannot easily tell that the skill may perform outbound requests or handle sensitive runtime inputs such as API credentials.
The manifest description focuses on parsing obfuscated number text and calculating answers. This file goes beyond solving by implementing authenticated API submission of the answer to a remote service, which is a distinct write action not described in the stated behavior.
A math-challenge solver would be expected to parse text and compute a result locally. Handling bearer credentials and performing an authenticated POST introduces an account-affecting remote action that is not inherent in the manifest's narrowly stated purpose.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
"answer": f"{answer:.2f}"
}
response = requests.post(url, json=data, headers=headers)
result = response.json()
print(f"\n[Submit] {result.get('success', False)}")
This code performs a network request that transmits the provided API key in an Authorization header along with verification data, but there is no user confirmation prompt or explicit warning near the submission path about sending data to an external service. Although the CLI uses an explicit --submit flag, the file does not disclose the outbound transmission or credential use in comments, docstrings, or user-facing messaging before the request occurs.
The top-level documentation states "Moltbook Verification Challenge Solver v3.8," while the code prints "MOLTBOOK VERIFICATION SOLVER v3.7" during execution. This is a direct contradiction between documentation and actual reported behavior, even though it is not security-critical.
No suspicious patterns detected.