Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - `references/examples.md` — filled profiles for six different business types.
Security audit
Brand Profile
Security checks for vulnerabilities and agentic risk
Overview
This skill creates a local brand profile for social-media work and its file access and saved output are disclosed and purpose-aligned.
Before installing, understand that this skill will collect and save brand details, audience descriptions, proof points, guardrails, and example posts into a local project file that other social-media skills may reuse. Review that file for sensitive business information and use human or legal review for regulated claims.
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
- 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 (3)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The invocation cues are broad enough to match common onboarding or 'get started' requests, which can cause this skill to activate when the user did not specifically intend brand-profile setup. Because the skill is designed to run before other social media tasks and can redirect the workflow into profile collection, it may override user intent, create unnecessary data gathering, and interfere with correct skill routing.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 83% confidence
- Finding
Line L71 states 'First person always,' which is a natural-language instruction that forces a specific communication style. Because SQP-3 covers language/locale policy violations and this wording removes user choice, it can be interpreted as an organizational policy issue around mandated language style without opt-in.
- Content