Script + Custom Media

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 7:16 AM UTC
• Version: 1.0.0

Overview

This skill is a straightforward Revid video-rendering helper that sends a user-provided script and public media URLs to Revid, with no hidden persistence or unrelated local access found.

Install only if you are comfortable sending the script, media URLs, and Revid API-authenticated render requests to Revid. Use intentionally public media links, avoid private or sensitive assets unless you accept that exposure, and keep the REVID_API_KEY scoped and protected.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Undeclared Tool Scope

Medium

• Category: MCP Least Privilege
• Confidence: 88% confidence

Finding

The skill directs the agent to validate user-supplied media URLs and references an executable shell example, but it does not declare any tool restrictions or allowed-tools scope. That creates unnecessary ambiguity about what execution and network capabilities the agent may use, increasing the chance of over-privileged behavior such as arbitrary URL fetching or shell-based validation against attacker-controlled endpoints.

Content

No source excerpt is available for this finding.

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 70% confidence

Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · examples/run.sh (reported line 10)May include surrounding context.

sh

HERE="$(cd "$(dirname "$0")" && pwd)"
PAYLOAD=$(cat "$HERE/branded-script.json")

PID=$(curl -fsS https://www.revid.ai/api/public/v3/render \
  -H "Content-Type: application/json" -H "key: $REVID_API_KEY" \
  -d "$PAYLOAD" | jq -r .pid)
echo "pid=$PID"

Missing User Warnings

Low

• Category: Not specified by scanner
• Confidence: 84% confidence

Finding

This markdown skill instructs users to supply public media URLs, and later directs validation that each URL returns 200, which implies external network retrieval of user-provided assets. While the input note says URLs must be public, it does not explicitly warn users about the privacy implication that assets will be fetched by a third-party service and therefore should not contain sensitive or private content.

Content

No source excerpt is available for this finding.

Vague Triggers

Low

• Category: Not specified by scanner
• Confidence: 84% confidence

Finding

This JSON describes a workflow configuration but provides no invocation phrases, activation conditions, or exclusion criteria that clarify when the skill should be used. For manifest-style files, the absence of trigger specificity can make invocation behavior ambiguous if this file is used to define or advertise skill activation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.