v1.0.0

Ps Tool

BenignClawScan verdict for this skill. Analyzed Apr 30, 2026, 10:11 PM.

Analysis

This is a simple local process-listing skill with no network, credentials, or persistence, though users should know it can display visible process command lines and its documentation overstates some output features.

GuidanceThis appears safe to use as a basic local process viewer, but avoid sharing its output blindly because process command lines can contain sensitive arguments. Also verify expectations: the bundled script does not implement the documented CPU, memory, status, filter, or sort features.

Findings (3)

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.

Abnormal behavior control

Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.

Tool Misuse and Exploitation

SeverityLowConfidenceHighStatusNote

scripts/ps.py

for p in os.listdir('/proc'):
    if p.isdigit():
        ...
            print(f"{p:6} {cmd[:60]}")

The script enumerates visible process IDs under /proc and prints each process command line. This is purpose-aligned for a process viewer, but it exposes local process information that users should treat carefully.

User impactThe output may reveal running programs and command-line arguments, which can sometimes include sensitive details if shared.

RecommendationUse the tool intentionally and review process output before copying it into tickets, chats, or public logs.

Agentic Supply Chain Vulnerabilities

SeverityInfoConfidenceHighStatusNote

metadata

Source: unknown
Homepage: none

The registry information does not provide an upstream source or homepage. This is a provenance note rather than a concern because the provided package is small, contains no dependencies or install script, and includes the full script content for review.

User impactUsers have less external provenance information for verifying the publisher or upstream project.

RecommendationReview the bundled files and publisher before installation, especially if using it on systems where process listings may be sensitive.

Human-Agent Trust Exploitation

SeverityLowConfidenceHighStatusNote

scripts/ps.py

print(f"{p:6} {cmd[:60]}")

The implementation prints only the PID and truncated command line, while SKILL.md describes CPU usage, memory consumption, status, sorting, and filtering options. This is a functionality accuracy issue users should notice, not evidence of deception or high-impact abuse.

User impactA user might expect resource-usage diagnostics that the included script does not actually provide.

RecommendationTreat the output as a basic PID/command listing unless the documentation or implementation is updated to support CPU, memory, status, filtering, and sorting.