Openclaw Triage

PassAudited by ClawScan on May 1, 2026.

Overview

This is a coherent local forensic triage skill, but it intentionally reads broad workspace contents and stores local evidence, so users should treat its output directory as sensitive.

This skill appears suitable for local incident response. Before installing or running it, confirm the workspace path, expect broad local file inspection, and protect the .triage evidence directory because it can contain sensitive forensic records.

Findings (4)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

The agent can invoke a script that reads many files in the selected workspace and produces security findings.

Why it was flagged

The skill runs a local Python tool over a workspace and performs broad forensic analysis. This is appropriate for incident response, but users should ensure they point it at the intended workspace.

Skill content
Collects workspace state, checks for signs of compromise ... cross-references with warden/ledger/signet/sentinel data
Recommendation

Run it only against workspaces you intend to investigate, and review the selected --workspace path before evidence collection.

What this means

If secrets are present in the workspace, the triage report may reveal their presence or related evidence.

Why it was flagged

The skill may read files containing tokens or secrets to detect exposure. That is purpose-aligned for compromise triage, and the artifacts do not show credential transmission or unrelated account use.

Skill content
checks for credential exposure patterns in recently modified files
Recommendation

Protect triage outputs as sensitive and avoid sharing reports or evidence directories without review.

What this means

Users may rely on an external repository not reflected in the registry source metadata.

Why it was flagged

The registry lists the source as unknown and no homepage, while the README points to a GitHub repository for installation. This is not suspicious by itself, but it is a provenance detail users should notice.

Skill content
git clone https://github.com/AtlasPA/openclaw-triage.git
Recommendation

Install from a trusted source and verify that the installed files match the reviewed package.

What this means

Triage evidence may remain on disk after the investigation and could expose workspace structure, hashes, timestamps, or security-tool records.

Why it was flagged

Evidence collection persists forensic metadata and copied security-tool data locally. This is expected for incident response, but persistent evidence can contain sensitive workspace history.

Skill content
Saves everything to `.triage/evidence-{timestamp}/` or a custom directory
Recommendation

Store evidence directories securely, restrict access, and delete or archive them according to your incident-response policy.