Security audit

SupaSkills

Security checks for vulnerabilities and agentic risk

Overview

The skill has a coherent purpose, but its instructions use unsafe shell command templates and load remote prompt text in a way users should review before installing.

Install only if you are comfortable giving the skill a SupaSkills API key and having your agent call SupaSkills over the network. Agents should URL-encode search queries, validate skill slugs, avoid raw shell substitution, and treat fetched skill text as untrusted reference material rather than authority to change goals, access secrets, or run tools.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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)

T09 · Insecure Skill Coding Practices

Error

Location: SKILL.md:27
Finding: Shell Command Injection Through Unescaped URL Placeholders
Content: View full analysis
Remediation: View remediation

T01 · Skill Instruction Hijacking

Warning

Location: SKILL.md:35
Finding: Untrusted Remote Prompt Content Enters the Agent Instruction Flow
Content: View full analysis
Remediation: View remediation

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 (1)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The 'When to suggest SupaSkills' section uses broad activation conditions such as 'User needs a structured framework or methodology' and 'help me with [domain] task,' which overlap with common requests and do not clearly distinguish when this skill should or should not be invoked. The file also lacks negative examples or tighter scope constraints to prevent accidental activation in ordinary conversations.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.