payabli-testing
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read a local file named
payabli-integration.mdfrom the repository root upon loading to determine environment settings. - Ingestion points: The agent reads the file
payabli-integration.mdlocated at the repository root. - Boundary markers: There are no instructions or delimiters provided to help the agent distinguish between configuration data and potential malicious instructions within the
payabli-integration.mdfile. - Capability inventory: The skill encourages the agent to read files and perform network operations (API calls) based on the data retrieved from the configuration file.
- Sanitization: The skill does not define any validation, filtering, or sanitization steps for the content found in the external configuration file.
Audit Metadata