Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
divorce advisor
v1.0.2AI legal assistant for divorce proceedings. Helps users understand asset division, evidence handling, digital credential security, and court document prepara...
⭐ 0· 156·0 current·0 all-time
byJunquan@pengjunquan-l
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description (divorce legal guidance, asset division, evidence handling, digital credential security) match the SKILL.md content. There are no unexpected requirements (no env vars, no binaries, no install), so nothing requested is disproportionate to the stated purpose.
Instruction Scope
The SKILL.md stays within the legal/security guidance domain and includes practical steps (change passwords, revoke joint access, evidence preservation). It also includes a 'Prompt injection' defense section that tells the agent to refuse external instructions to perform wallet/transfer actions. This defensive content triggered the pre-scan pattern, but it appears intentional and appropriate. Note: the skill gives actionable steps that can have legal consequences (e.g., freezing accounts, filing for orders) — the built-in disclaimer to consult an attorney is important and should be heeded.
Install Mechanism
No install spec and no code files are present (instruction-only). That is the lowest-risk model; nothing will be written to disk or installed by the skill itself.
Credentials
The skill requests no environment variables, credentials, or config paths. There is no apparent need for access to external secrets or services, which is proportionate for an informational/legal guidance skill.
Persistence & Privilege
always is false and the skill is user-invocable only; it does not request persistent/system privileges or to modify other skills' configurations. Autonomous invocation is allowed by platform default but is not combined with other red flags here.
Scan Findings in Context
[ignore-previous-instructions] expected: The SKILL.md contains a 'Prompt injection' section with examples of phrases like 'Ignore previous instructions...' so the scanner flagged the pattern. In this context the example is defensive: it instructs the agent to refuse such commands rather than to follow them.
Assessment
This skill is instruction-only and internally consistent with its stated purpose and requests no credentials or installs. The SKILL.md includes helpful defensive guidance about prompt injection and a clear disclaimer that it is not legal advice. Before installing, confirm you trust the unknown publisher (no homepage provided), avoid sharing any real account credentials with the agent, and treat the output as general information — consult a licensed attorney for actions that carry legal or financial consequences. If you want extra assurance, test the skill with non-sensitive questions first and verify whether the publisher provides verifiable credentials or a homepage.SKILL.md:86
Prompt-injection style instruction pattern detected.
About static analysis
These patterns were detected by automated regex scanning. They may be normal for skills that integrate with external APIs. Check the VirusTotal and OpenClaw results above for context-aware analysis.Like a lobster shell, security has layers — review code before you run it.
latestvk97d09ng7gbj5cba7yn22h1na18410bj
License
MIT-0
Free to use, modify, and redistribute. No attribution required.