ClawHub

Investigation Pack (ACAS-aligned)

v1.0.0

Generates ACAS-aligned investigation invite wording, neutral question sets, and evidence logs. USE WHEN starting a driver incident investigation/interview.

⭐ 1· 1.7k·0 current·0 all-time
by@kowl64
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
ℹ
Purpose & Capability
The name, description, and bundled templates (invite wording, question plan, evidence log, ACAS checklist) align with the stated purpose of producing ACAS-aligned investigation materials. Nothing in the skill requests unrelated system access or credentials. Note: the skill's source/homepage are missing which reduces traceability but does not make the content incoherent.
✓
Instruction Scope
SKILL.md confines runtime actions to drafting documents from the provided templates and asking the user for required incident inputs. It explicitly instructs the agent to STOP AND ASK when the stage is unclear and warns not to give legal advice. It does not instruct reading system files, calling external endpoints, or exfiltrating data.
✓
Install Mechanism
No install spec and no code files (instruction-only). This is the lowest-risk model: nothing will be downloaded or written to disk by the skill itself.
✓
Credentials
The skill declares no required environment variables, credentials, or config paths. The optional inputs are case materials and internal policy text (user-supplied), which are appropriate and proportional for drafting investigation documents.
✓
Persistence & Privilege
The skill does not request permanent presence (always:false) or any special privileges, and it does not instruct modifying other skills or system settings. Autonomous invocation is allowed by platform default but is not used to escalate privileges here.
Assessment
This skill appears coherent and low-risk from a technical perspective, but consider these practical points before installing or using it: - Verify templates with your organisation's HR/legal team before sending them to employees or using them in live cases — the skill explicitly says not to provide legal advice. - Do not paste unnecessary sensitive personal data (e.g., national IDs, medical records) into the tool when requesting outputs; supply only the incident details needed. - Confirm the matter is at an investigation (fact-finding) stage before using the templates — the skill correctly instructs to STOP AND ASK if the stage is unclear. - Because the skill’s source/homepage is not provided, consider vetting the content (templates/checklist) against your organisation’s policies and local employment law before wide adoption. - Keep audit/logs of any documents produced and shared, and ensure evidence handling and retention complies with your internal chain-of-custody practices.

Like a lobster shell, security has layers — review code before you run it.

latestvk972ae48gn6fryh65xef3fmc797zczrk

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments