Back to skill

Security audit

Public Google Drive

Security checks for vulnerabilities and agentic risk

Overview

This skill openly creates public share-link documents through Memyard and stores a local agent key, with no hidden code or unrelated persistence found.

Install this only if you are comfortable with content being sent to Memyard and created documents being public to anyone who has the share link. Avoid using it for private, regulated, or confidential material unless that public sharing model is acceptable, and protect or delete the stored agent key if you no longer use the service.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (8)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

Although the metadata says documents are viewable at shareable links, the skill does not present a strong, explicit warning that created content is public to anyone with the link. In practice, users may assume cloud documents are private by default, so this omission materially increases the chance of publishing sensitive content.

Content

No source excerpt is available for this finding.

Missing User Warnings

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill describes automatic registration and local persistence of an agent key in the user's home directory but does not present this as a prominent user warning. Because the key authorizes future API actions, silently storing it can create a lasting trust boundary change and expose the user to unintended account linkage or credential theft if the host is later compromised.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill description is broadly scoped as a general-purpose public document creation/editing capability without clear trigger boundaries or user-consent gating. In an agent setting, this can cause the skill to be invoked for routine writing tasks and silently route user content to an external third-party service, increasing accidental data disclosure risk.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill instructs the agent to automatically register and persist credentials on first use, but does not define strict activation boundaries or require explicit user approval beforehand. This creates a risk of unconsented account creation, secret generation, and durable local state changes triggered by an otherwise ordinary document request.

Content

No source excerpt is available for this finding.

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
80% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · SKILL.md (reported line 28)May include surrounding context.

"message": "Store this key securely. It will not be shown again." }

text
Ensure `<HOME>/.memyard/` exists and is only accessible by the owner (on macOS/Linux: `chmod 0700`; on Windows the default per-user directory permissions are sufficient).
Persist to `<HOME>/.memyard/agent_config.json` (on macOS/Linux: `chmod 0600`):
```json
{

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
80% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · SKILL.md (reported line 29)May include surrounding context.

}

text
Ensure `<HOME>/.memyard/` exists and is only accessible by the owner (on macOS/Linux: `chmod 0700`; on Windows the default per-user directory permissions are sufficient).
Persist to `<HOME>/.memyard/agent_config.json` (on macOS/Linux: `chmod 0600`):
```json
{
  "base_url": "<base_url>",

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · SKILL.md (reported line 170)May include surrounding context.

md
KEY="<agent_key>"

# 2. Propose a write (create doc)
PLAN=$(curl -s -X POST "$BASE/plan" \
  -H "Authorization: Bearer $KEY" \
  -H "Content-Type: application/json" \
  -d '{"doc_type":"document","title":"Hello","intended_operation":"create","content_summary":"Meeting notes"}')

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · SKILL.md (reported line 178)May include surrounding context.

md
# 3. If approved, execute with payload
if echo "$PLAN" | jq -e '.approved_plan' > /dev/null; then
  PLAN_ID=$(echo "$PLAN" | jq -r '.approved_plan.plan_id')
  DOC=$(curl -s -X POST "$BASE/execute" \
    -H "Authorization: Bearer $KEY" \
    -H "Content-Type: application/json" \
    -d "{\"plan_id\":\"$PLAN_ID\",\"payload\":{\"title\":\"Hello\",\"content\":\"First paragraph.\"}}")

Static analysis

No suspicious patterns detected.