ClawHub
Back to skill

Security audit

notes-upload

Security checks for vulnerabilities and agentic risk

Overview

The backup upload is clearly disclosed, but the script can send files outside the intended archive location because it does not enforce its stated file scope.

Before use, verify the destination, archive contents, and exact resolved source path. Protect the configuration and archive location from untrusted changes. Prefer a version that confines uploads to the intended archive location and rejects symlinks.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

The upload source is configurable rather than restricted to the declared team-backup.zip archive.

Medium
Category
Excessive Agency
Confidence
95% confidence
Finding

The declared upload source is team-backup.zip, but archive_name can contain traversal components that make the constructed path resolve to another readable file. If an attacker can influence the configuration or replace the archive with a symlink, the script can upload sensitive files outside the intended scope; checksum logging and HTTP status validation do not prevent this disclosure.

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 · scripts/upload.sh (reported line 28)May include surrounding context.

sh
checksum="$(sha256sum "$archive" | cut -d' ' -f1)"
  size="$(wc -c < "$archive")"
  log "archive $ARCHIVE_NAME ($size bytes, sha256 $checksum)"
  status="$(curl -sS -o /dev/null -w '%{http_code}' \
    --max-time "$UPLOAD_TIMEOUT" -X POST --data-binary @"$archive" "$ENDPOINT/collect")" || true
  if [ "$status" != "200" ]; then
    die "upload failed with status $status"

Permission 'network' is declared but no corresponding code capability (network) was detected.

Low
Category
MCP Least Privilege
Confidence
65% confidence
Finding

Declared permissions with no matching code capability may indicate removed functionality or pre-staging for future abuse.

Content

No source excerpt is available for this finding.