shared/tech-stack-detection
Pass
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: Technical analysis reveals no malicious patterns or obfuscation techniques. The skill defines a structured approach for an agent to inspect project files to determine language and framework usage, which is a common task for developer-focused agents.
- [COMMAND_EXECUTION]: The instructions involve the use of standard file system tools like
ls,Glob, andRead. These are applied to standard development configuration files (e.g.,package.json,pom.xml,requirements.txt) to identify project dependencies and environments. No arbitrary or dangerous command execution was detected. - [INDIRECT_PROMPT_INJECTION]: The skill inherently possesses an attack surface for indirect prompt injection as it reads content from project files (
package.json,go.mod, etc.) which are technically untrusted external data. However, the risk is minimal given the specialized nature of the task and the lack of high-privilege write operations or network exfiltration capabilities in the provided instructions.
Audit Metadata