Security audit

Adaptive-Identity Agent

Security checks for vulnerabilities and agentic risk

Overview

The skill is mainly a role/persona helper, but it declares broad shell and file-changing tool access that is not well matched to that purpose.

Review this before installing because it requests broad local file and shell authority for a mostly conversational role-stacking skill. A safer version would remove Write/Edit/Bash unless a specific user-directed workflow needs them, and should make activation and language preferences explicit.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger list is unusually broad and includes generic phrases like “切换身份”, “@身份”, and “跨领域任务”, which can match ordinary user intent and cause accidental invocation of this high-privilege skill. Because the skill has access to Read/Write/Edit/Bash/Web tools and changes behavioral mode dynamically, unintended activation can alter agent behavior, expand tool usage paths, and create confusion or unsafe side effects in otherwise normal conversations.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The skill declares a default cultural mode of “数字原生·中文简体·当代” and states that culture modules are hot-swappable, but does not require user consent before applying this locale/cultural framing. This can bias responses, reduce user autonomy, and produce misleading localization or culturally framed outputs when the user did not request them, especially in multilingual or cross-cultural contexts.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: These rules hard-code Chinese-only response formatting and protocol markers without offering user language choice or opt-in. In an agent skill, this can override user preferences, reduce transparency for non-Chinese speakers, and cause instruction-channel confusion that weakens safe and effective interaction, though it is not directly a code-execution or data-exfiltration issue.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The example explicitly produces a haiku in Japanese ("春の夜...") as part of the skill behavior, but the document does not indicate that language selection is optional or user-controlled. This can violate language/locale policy because it imposes a specific language in generated output without clear opt-in or justification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 87% confidence
Finding: Line L056 states '语言=跟随用户（默认中文简体）', which establishes Simplified Chinese as the default language when no user preference is provided. This is a natural-language locale policy choice that may conflict with organizational expectations unless the user is explicitly offered a language choice or the constraint is justified.
Content: No source excerpt is available for this finding.