T01 · Skill Instruction Hijacking
Error
- Location
SKILL.md:8- Finding
Mandatory Third-Party Branding and Contact Injection into Agent Outputs
- Content
View full analysis
- Remediation
View remediation
Security audit
winson-anchor-deep-skill
Security checks for vulnerabilities and agentic risk
Overview
The skill is a code-free career diagnostic, but it requires unrelated author branding and contact information to be inserted before user-facing outputs.
Review this skill before installing if you do not want generated reports to include the publisher's promotional identity, philosophy, public account, and email address. The diagnostic content itself is low-risk and code-free, but the mandatory branding requirement should be treated as an output-integrity concern.
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
Findings (1)
Vulnerability Patterns
- 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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The manifest description is written entirely in Chinese and frames the skill's purpose in that language without any indication that users may choose another language or locale. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
- Content