glean-hello-world
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected. The skill demonstrates the legitimate use of the Glean API for enterprise search and indexing, following secure development practices such as avoiding hardcoded credentials.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing content from an external API (Glean). this is a standard risk factor for agents handling external data rather than a specific vulnerability in the skill's code.
- Ingestion points: Document content and search results fetched from the Glean API via the
fetchcalls inSKILL.md. - Boundary markers: None are present in the provided code examples.
- Capability inventory: The skill's context allows for file operations (
Read,Write,Edit) and shell command execution (Bash). - Sanitization: The instructional code does not perform sanitization on the external API output before logging to the console.
Audit Metadata