v0.1.0

Stock Monitor Skill 0.1.0

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 7:21 AM.

Analysis

This appears to be a purpose-aligned stock alert tool, but users should notice that it can run as a background daemon and contact third-party market/news APIs.

GuidanceBefore installing, verify the package source, review the hardcoded watchlist and cost values, and only start the daemon if you want ongoing monitoring. Stop it when not needed, and do not treat its market suggestions as guaranteed financial advice.

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.

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.

Agentic Supply Chain Vulnerabilities

SeverityLowConfidenceMediumStatusNote

_meta.json

"ownerId": "kn70aj13hr3z4fpmfk1y2jmpz181gn2z", "slug": "stock-monitor-skill"

The embedded metadata does not match the supplied registry owner/slug, and the registry source is unknown. This is a provenance/package-quality gap users should verify before running code.

User impactA user may have less assurance that the package identity and source history are cleanly traceable.

RecommendationVerify the publisher/source before installing, and prefer a package with consistent registry and embedded metadata.

Rogue Agents

SeverityLowConfidenceHighStatusNote

scripts/control.sh

nohup python3 "$SCRIPT_DIR/monitor_daemon.py" > "$LOG_DIR/monitor.log" 2>&1 &
echo $! > "$PID_FILE"

The control script starts a background process and records its PID. This is disclosed and has stop/status commands, but it means the skill can keep running after the initial invocation.

User impactThe monitor may continue making periodic checks and writing logs until the user stops it.

RecommendationStart it only when continuous monitoring is desired, and use `./control.sh stop` when finished.

Human-Agent Trust Exploitation

SeverityInfoConfidenceHighStatusNote

SKILL.md

💡 Kimi建议:
🚀 多条件共振，趋势强劲，可考虑继续持有或分批减仓。

The skill presents investment-style recommendations. The same document includes cautionary usage tips, so this is a user-awareness note rather than a deception concern.

User impactUsers could over-rely on automated investment suggestions if they treat alerts as authoritative advice.

RecommendationTreat alerts as informational only and verify with independent financial judgment before making trades.

Sensitive data protection

Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.

Insecure Inter-Agent Communication

SeverityLowConfidenceHighStatusNote

scripts/analyser.py

url = "https://searchapi.eastmoney.com/api/suggest/get" ... url = f"https://search.sina.com.cn/?q={name}&c=news&sort=time"

The analysis component sends stock identifiers/names to third-party financial/news services. This is expected for a market monitor, but it is still an external data flow.

User impactStocks being monitored may be revealed to external market/news API providers.

RecommendationAvoid entering highly sensitive private portfolio details if you do not want related stock names/codes queried against those services.