Back to skill

Security audit

elite-writing-skill

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only writing-assistance skill with broad writing triggers and persuasive templates, but I found no hidden execution, data access, persistence, or exfiltration behavior.

Install this if you want Indonesian/English writing, editing, documentation, and copywriting help. Review marketing outputs for truthful claims, genuine urgency, consent-based outreach, privacy, and applicable anti-spam rules, and treat API/curl snippets as placeholders rather than commands to run unchanged.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The README consistently instructs users in Indonesian and does not state that the skill is intended only for Indonesian-speaking users or provide an opt-in language choice. This can violate language/locale policy when a skill effectively forces one language for general use without user selection.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill advertises broad activation triggers such as 'tulis', 'buat copy', 'draft artikel', and 'perbaiki tulisan', which can cause the skill to auto-activate for a wide range of ordinary writing requests. Over-broad activation increases the chance the agent routes unrelated or sensitive tasks into this skill, expanding its authority and making prompt-scope mistakes more likely even though the skill itself is not overtly malicious.

Content

No source excerpt is available for this finding.

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 · references/technical-writing.md (reported line 202)May include surrounding context.

EXAMPLE:

bash
curl -X POST https://api.example.com/v1/resource \
  -H "Authorization: Bearer {token}" \
  -H "Content-Type: application/json" \
  -d '{"field1": "value"}'

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · references/technical-writing.md (reported line 202)May include surrounding context.

EXAMPLE:

bash
curl -X POST https://api.example.com/v1/resource \
  -H "Authorization: Bearer {token}" \
  -H "Content-Type: application/json" \
  -d '{"field1": "value"}'

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

The file presents user-facing operational instructions partly in Indonesian and partly in English, including an English mission and protocol language, but does not state whether the user can choose their preferred language. This can create an implicit language policy or default without opt-in.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The template explicitly structures a persuasive sales sequence using pain amplification, social proof, urgency, and objection handling, but provides no guardrails around consent-based outreach, truthful claims, or privacy-safe use of recipient data. In a writing skill, this is not inherently malicious, but it can normalize manipulative email practices and facilitate non-compliant marketing if used without ethical and legal constraints.

Content

No source excerpt is available for this finding.