sn-report-format-discovery
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input to determine a format string, which creates a surface for indirect prompt injection. However, the skill's capabilities are extremely limited; it is restricted to returning a single line of text and explicitly prohibits file creation or external searches.
- Ingestion points: The skill ingests user-provided
queryandlanguageinputs. - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are defined for the input data.
- Capability inventory: The skill does not possess tools for file writing, network access, or command execution, and rules specifically forbid creating files or searching external specifications.
- Sanitization: There is no evidence of input sanitization or validation performed on the user query.
Audit Metadata