csharp-best-practices
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied input to retrieve specific documentation topics. \n
- Ingestion points: Untrusted data enters the agent context via the
$ARGUMENTSvariable inSKILL.md. \n - Boundary markers: Absent. There are no delimiters or explicit instructions to treat the input as data only. \n
- Capability inventory: The skill uses
Read,Glob, andGreptools as defined inSKILL.md. \n - Sanitization: Absent. The topic provided by the user is not validated or sanitized before being used for file lookup operations.
Audit Metadata