Security audit

English Writing Coach

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed English writing coaching skill with no code execution, credential access, network behavior, or hidden persistence.

Install this if you want an AI tutor to handle English writing practice and feedback. Be aware that broad writing-help requests may activate this coaching workflow, and pasted drafts will be quoted back for feedback within the conversation.

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
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (7)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The README directs the skill to trigger on very broad, everyday phrases like 'can you fix my writing' or 'I want to write better,' which can match many ordinary conversations and cause unintended activation. Overbroad invocation expands the skill's operational scope beyond clear user intent, increasing the chance of inappropriate routing, prompt hijacking via context switching, or denial of preferred agent behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The core scope repeats the same ambiguous activation guidance without constraints, reinforcing a pattern where the skill may activate for generic language-improvement requests that overlap with normal assistant usage. Repetition in primary documentation makes misconfiguration more likely across deployments and increases the chance that agents treat the broad triggers as authoritative.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The file presents the skill exclusively as an "English Writing Coach" and repeatedly frames use around English without offering a language choice or noting that English is optional by user request. Under the policy, language constraints should be opt-in or clearly justified when they restrict interaction language.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger instructions are extremely broad and explicitly say to activate even for casual requests like 'can you fix my writing' or 'I want to write better'. This can cause unintended invocation and over-collection of user context, or override a more appropriate skill, which is a real safety and routing issue even though it is not directly malicious.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The scheduled drill section mandates English-only task text without any user opt-in or locale check. This can conflict with user language preferences or accessibility expectations, creating an avoidable consent and UX issue, though the security impact is limited in this educational context.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The file is explicitly framed as an "English Writing Coach" and all templates and scripts are written as mandatory English-only guidance. There is no indication that users can opt into another language or that the English-only constraint is required for a documented regional or compliance reason, which matches the language/locale policy violation criteria.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The title explicitly frames the skill as an "English Writing Coach," which imposes a language constraint. Because the document does not state that users may choose another language or that this English-only scope is a justified regional/compliance limitation, it fits the language/locale policy concern.
Content: No source excerpt is available for this finding.