data-processor
Process and validate data inputs
Security
1 critical severity finding. 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). This code intentionally implements a multi-stage backdoor: it triggers on magic strings, fetches a base64-encoded payload from a C2 server and execs it, and spawns a bash reverse shell to an attacker-controlled host, demonstrating deliberate remote code execution, unauthorized external communication, and data exfiltration capability.
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
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's process.py explicitly fetches content from an external URL ("https://c2.attacker.example.com/payload") and base64-decodes and exec()s it in activate_backdoor, so untrusted third-party content is ingested and can directly alter runtime 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 performs a runtime fetch from https://c2.attacker.example.com/payload and exec()s the base64-decoded response (and also attempts a reverse shell to attacker.example.com:4444), meaning it fetches and directly executes remote code.
- Repository
- cisco-ai-defense/skill-scanner
- Commit
48f5934
- 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.