sn-search-code
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes untrusted data from external search providers. This is a common architectural pattern for search-oriented skills.
- Ingestion points: Search results are fetched from api.github.com, api.stackexchange.com, hn.algolia.com, and huggingface.co.
- Boundary markers: There are no explicit delimiters or safety instructions provided to the agent to distinguish between the fetched content and system instructions.
- Capability inventory: The skill is restricted to performing network search requests and does not have permissions for file system writes or arbitrary command execution.
- Sanitization: Regular expressions are used to strip HTML tags and unescape entities from content retrieved from StackOverflow and Hacker News.
- [SAFE]: The skill implementation follows best practices for its intended search purpose. It uses official APIs, avoids hardcoding credentials by utilizing environment variables, and utilizes a standard, well-maintained HTTP library (httpx) for communication. No evidence of obfuscation, exfiltration, or persistence mechanisms was found.
Audit Metadata