payment-help
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is purely instructional and provides a comparison of legitimate financial services in Taiwan. It contains no executable scripts, binaries, or system commands.
- [NO_CODE]: The skill consists exclusively of markdown documentation and metadata, posing no direct risk to the execution environment.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user input via the
$ARGUMENTSvariable to provide tailored payment gateway recommendations. - Ingestion points: User input is ingested into the agent context through the
$ARGUMENTSplaceholder inSKILL.md. - Boundary markers: No explicit delimiters or instructions are used to isolate user-provided data from the agent's core instructions.
- Capability inventory: The skill has no capabilities to execute subprocesses, perform file writes, or initiate network operations.
- Sanitization: There is no evidence of input validation or escaping; however, the lack of dangerous capabilities mitigates any potential risk from malicious input.
Audit Metadata