Security audit

Work Productivity Pollyreach Gives Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a low-impact workflow helper with overly broad activation wording, but it contains no executable code, hidden data access, persistence, or credential handling.

Before installing, be aware that this skill may be selected too often because its trigger terms are broad and implicit invocation is enabled. It is otherwise a documentation-style helper, so review whether you want it available automatically for general productivity requests.

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

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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 (14)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger sentence is extremely broad and matches ordinary user language about getting help, which can cause unintended activation outside the intended PollyReach workflow context. In agent ecosystems, overbroad invocation patterns can route unrelated tasks into this skill, producing incorrect behavior, prompt interference, or accidental execution of workflow-specific instructions on unrelated requests.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 94% confidence
Finding: This trigger pattern is a generic request template ('I need a practical workflow for ...') with little meaningful constraint, so many benign requests could unintentionally match it. Because the skill is positioned as a reusable helper, broad matching increases the chance of accidental invocation and context hijacking, especially in multi-skill or automated routing environments.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger phrase and keyword set include broad, everyday terms like phone, number, ability, things, and done, which can cause the skill to activate in unrelated conversations. In an agent ecosystem, unintended invocation can route user requests into the wrong workflow, causing confused execution, privacy exposure in context sharing, or unsafe action chaining.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger list includes very generic everyday words such as "every," "phone," "number," "ability," and "things," which can cause the skill to activate in many unrelated conversations. This creates prompt-routing confusion and increases the chance the agent invokes the wrong skill, leading to irrelevant actions, degraded reliability, or accidental execution of workflows in the wrong context.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The example trigger phrases rely on generic language like "Help me" and "I need," which are common across a huge range of normal user requests. If these examples are used by routing or embedding-based invocation systems, they can bias the skill toward matching broad, unrelated prompts and cause unintended activation.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger keyword list includes extremely common words such as "every", "phone", "number", "ability", "things", and "done", which can cause the skill to activate in many unrelated conversations. This creates prompt-routing risk: users may be steered into this skill unintentionally, producing irrelevant workflow behavior and potentially overshadowing safer or more appropriate skills.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger sentence is so broad and generic that it can cause the skill to activate for unrelated user requests, increasing the chance of misrouting or over-invocation. In an agent ecosystem, overly broad activation rules can create unsafe or unintended handling paths, especially when the skill is framed as applicable to many common work-productivity situations.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The activation guidance is ambiguous and does not clearly define when the skill should or should not run. This increases the chance of accidental activation and misrouting, especially in automated agent selection systems that rely on README keywords and examples as routing signals.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 83% confidence
Finding: The file presents itself specifically as the Chinese-language user guide ("README.zh-CN.md" / 中文版用户说明) without any language-choice or opt-in language in the content. This can indicate a locale-specific presentation without explicitly offering the user an alternative within the file.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The description says to use the skill when users mention broad terms or need general workflow artifacts, analysis, or implementation support, but it does not clearly define scope boundaries. That ambiguity increases the chance of overbroad matching and accidental invocation for requests that are only loosely related to the intended PollyReach-style use case.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The example trigger phrases begin with highly generic constructions like "Help me" and "I need a practical workflow," which are common across many benign requests. Without negative examples or disambiguation guidance, these samples reinforce permissive matching behavior and make accidental triggering more likely.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The default prompt is overly broad and includes generic terms like 'help me' and a long natural-language description that can match many ordinary user requests. This raises the chance of unintended skill invocation, which can insert this skill's behavior into unrelated conversations and cause unexpected actions or misleading assistance.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: Enabling implicit invocation without strong activation constraints allows the skill to be invoked based on loose semantic matches rather than clear user choice. In this context, the broad productivity/workflow theme makes accidental activation more likely, which can lead to prompt-scope confusion, unwanted tool behavior, or interference with other agent tasks.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The invocation guidance uses a broad request pattern that lacks clear boundaries, which can lead an orchestrator or user to apply this skill far outside its intended domain. That increases the risk of incorrect automation, unnecessary context capture, and accidental substitution for more appropriate domain-specific skills.
Content: No source excerpt is available for this finding.