validating-cors-policies
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from both the local codebase (via Grep) and external web endpoints (via WebFetch). While it does not execute this data as code, the agent's analysis could be influenced by malicious content embedded in the scanned files or HTTP responses.
- Ingestion points: SKILL.md instructions 1 and 9 involve reading file content and fetching remote URLs.
- Boundary markers: Absent. The instructions do not specify using delimiters to isolate untrusted content.
- Capability inventory: Grep (file read), WebFetch (network access), and script execution (local Python scripts).
- Sanitization: Absent. The skill analyzes raw headers and code snippets without explicit sanitization steps.
Audit Metadata