AI legal assistant for divorce proceedings. Helps users understand asset division, evidence handling, digital credential security, and court document prepara...
Security Analysis
high confidenceThis is an instruction-only legal guidance skill whose instructions align with its stated purpose, requires no credentials or installs, and contains defensive guidance about prompt injection.
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.
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.
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.
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.
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.
Guidance
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.
Latest Release
v1.0.2
- Added section on prompt injection, warning users about risks from malicious instructions in external content. - Provided guidance on how to recognize and refuse suspicious or coercive wallet operation requests. - Clarified safe execution requirements for sensitive actions, emphasizing user confirmation and verification.
Popular Skills
Published by @pengjunquan-l on ClawHub
