ClawHub

Incident Dossier

v1.0.0

Build a concise incident dossier from operational logs, audits, JSON/JSONL files, and state snapshots. Use when investigating failures, duplicate events, stu...

⭐ 0· 104·0 current·0 all-time
by@neo1307
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 skill is an incident-dossier generator and includes a JS script that parses JSON/JSONL evidence and emits a Markdown report — this matches the name and description. One minor inconsistency: SKILL.md instructs running the script with node, but the registry metadata lists no required binaries; the script therefore implicitly requires a Node.js runtime that is not declared.
✓
Instruction Scope
SKILL.md restricts actions to parsing provided evidence files and producing an output dossier. It explicitly instructs the agent to invoke the included script with explicit --input paths and an --out path and includes guardrails (do not fabricate timestamps, verify raw lines). There are no instructions to read unrelated system files or environment variables.
✓
Install Mechanism
There is no install spec (instruction-only skill plus a local script). No downloads, remote installs, or archive extraction are present. The only runtime requirement is executing the provided Node.js script locally.
✓
Credentials
The skill declares no environment variables, credentials, or config paths, and the code does not access environment secrets. It only reads files supplied as inputs and writes the output file.
✓
Persistence & Privilege
always is false and the skill does not request persistent or elevated privileges, nor does it modify other skills or global agent configuration. It only creates the specified output file.
Assessment
This skill appears coherent and runs entirely on files you provide. Before installing/using: ensure your agent environment has Node.js available (SKILL.md expects to run node), only pass intended evidence files (do not feed secrets or unrelated system files), and review the generated dossier against raw lines as the skill itself recommends. There are no network calls or hidden endpoints in the code, but exercise standard caution about what files you hand to any automated processor.

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

latestvk970sf9dhr1q3wxgfypvx3y4q5839z9f

License

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

Comments