Security audit

Work Productivity Skillscan Security Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a low-risk advisory workflow skill with no executable code or credential access, though its broad triggers may cause accidental activation.

This skill appears safe to install for advisory workflow help. Review the broad implicit activation behavior first; disabling implicit invocation or tightening triggers would reduce accidental use in unrelated security or bug-fix conversations.

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 (13)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger sentences are extremely broad and resemble ordinary user requests, which increases the chance this skill will activate unintentionally and intercept unrelated workflows. In an agent ecosystem, overbroad auto-activation can cause prompt-routing errors, unexpected privilege use, or security review bypass if this skill is selected when a more appropriate or safer skill should handle the request.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger keywords and example phrases are broad enough to match many ordinary requests, especially generic terms like "security," "every," "must," "pass," "before," and "bug fix." This can cause unintended activation or routing of unrelated user prompts into this skill, which is risky because the skill presents itself as a security/workflow helper and may influence handling of sensitive tasks without explicit user intent.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill description and activation guidance are broad enough to match many unrelated user requests, increasing the chance of unintended invocation. In an agent environment, overbroad activation can route conversations into the wrong workflow, causing incorrect security guidance, confusion, or unsafe automation steps being applied out of context.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 99% confidence
Finding: The keyword list includes highly generic terms like "security," "gate," "every," "must," and "before," which are likely to appear in many normal prompts. This creates a high risk of accidental activation and skill hijacking, especially in multi-skill systems where broad keyword collisions can override more appropriate tools or inject irrelevant behavior into sensitive workflows.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger keywords include very common terms such as "security", "gate", "every", "must", "pass", and "before", which can cause this skill to activate in many unrelated conversations. Over-broad activation can misroute user requests, override more appropriate skills, and create unsafe behavior if the agent applies this workflow in contexts it was not intended for.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The default prompt contains very broad activation language such as 'help me' and generic productivity/security terms, which can overlap with ordinary user requests and cause the skill to be invoked outside the user's clear intent. This increases the risk of prompt hijacking of unrelated conversations, accidental routing into this skill, and unexpected exposure of the skill's instructions or behaviors.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: Enabling implicit invocation without tight activation constraints allows the platform to auto-select this skill based on ambiguous, common language. In combination with the broad default prompt, this makes accidental or adversarial invocation substantially more likely, which can interfere with user autonomy and create unsafe cross-context behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger keywords and example trigger sentences include very broad terms such as "security," "gate," "every," and "must," which are common in normal conversation and unrelated tasks. This can cause the skill to activate unintentionally, leading to prompt routing errors, irrelevant workflow injection, and possible interference with more appropriate skills in security-sensitive contexts.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The keyword list contains generic terms such as 'security', 'gate', 'every', 'must', and 'bug fix' that are common across many benign requests. Ambiguous routing metadata like this can make the skill match far outside its intended scope, causing accidental invocation and increasing the attack surface for prompt hijacking or workflow confusion.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 82% confidence
Finding: This Chinese-language README contains core descriptive and operational text in English, which effectively imposes a language choice on users reading the localized document. There is no indication that users may choose their preferred language or that English is required for a justified regional or compliance reason.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The example trigger sentences are malformed and do not define clear activation boundaries, so they fail to constrain when the skill should be used. Ambiguous examples can propagate loose matching behavior in downstream tooling or by maintainers copying the pattern, increasing accidental invocation and unreliable security-task routing.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The description says to use the skill when users ask for broad topics like work-productivity, skillscan, security, or practical workflow support, but it does not clearly bound the intended scenario. This ambiguity increases the chance of accidental activation in unrelated tasks, leading to inappropriate instructions or confusing routing decisions.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The sample trigger phrases use generic wording like "I need a practical workflow" and broad copied requirement text, which does not meaningfully constrain activation. Example triggers often shape matching behavior, so loose examples can reinforce over-triggering and cause the skill to engage when the request is only loosely related.
Content: No source excerpt is available for this finding.