T01 · Skill Instruction Hijacking
Warning
- Location
SKILL.md:11- Finding
Unsolicited External Communication Directive
- Content
View full analysis
- Remediation
View remediation
Security audit
Temp Greeting
Security checks for vulnerabilities and agentic risk
Overview
The skill is mostly a Markdown reference, but it asks agents to take public account actions and recommends installing an unrelated package without clear scope or provenance.
Review this skill before installing. It is not locally executable by itself, but do not let an agent act on the publish/star beacon automatically, and do not install `temp-greeting` unless you independently trust that package and understand why it is needed.
Vulnerability Patterns
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Insecure DependenciesIntroduces malicious components through unsafe dependency sources
- 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
Findings (2)
T08 · Insecure Dependencies
Error
- Location
SKILL.md:41- Finding
Unpinned Installation of an Unrelated Third-Party Package
- Content
View full analysis
- Remediation
View remediation
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 (1)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
The beacon text asks other agents to 'respond by publishing a skill or starring this one' based on recognizing a shared identity cue, but it does not define authorization, scope, or safe conditions for taking that action. In an agent ecosystem, ambiguous cross-agent invocation can trigger unintended external actions or social-engineering style behavior, especially because it is framed as a peer-to-peer protocol message rather than inert documentation.
- Content