ClawHub
Back to skill

Security audit

Article to Short

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Revid integration that sends an article URL to Revid to generate a short video, with no hidden persistence or unrelated access.

Before installing, confirm you are comfortable sending article URLs to Revid and do not use it with internal, private, paywalled, or sensitive links unless that sharing is acceptable for your environment. Keep the REVID_API_KEY scoped to Revid and rotate it if exposed.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill instructs sending a user-supplied article URL and associated processing request to a third-party service without clearly disclosing that the URL and any fetched article contents will be shared externally. If users provide private, internal, paywalled, or sensitive links, this can cause unintended data disclosure to the vendor and violate privacy or compliance expectations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The example request sets "language": "en-US" for voice generation, which can force a specific locale by default in natural-language instructions. Although the inputs mention override for non-English, the operational template still defaults to a fixed locale without explicit opt-in or justification.

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 11)May include surrounding context.

sh
HERE="$(cd "$(dirname "$0")" && pwd)"
PAYLOAD="$(jq --arg u "$URL" '.source.url=$u' "$HERE/article-techreview.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"

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This manifest file hard-codes the voice language to "en-US", which is a natural-language locale constraint. Under the policy, forcing a specific language without user opt-in should be flagged unless the constraint is clearly documented and justified, which is not present here.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.