swiggy-pay
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands using the
swiggyCLI tool to check payment status and confirm orders. The commands involve passing parameters likepaasId,orderId, and geographic coordinates to the tool. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from external responses (such as the
place-orderoutput andmeta.message) and interpolates these into logic or reports them to the user, creating a potential vector for indirect instructions. - Ingestion points: The skill ingests data from the
place-orderresponse (paasId,orderId,addressId,lat,lng) and processes the output of theswiggytool (e.g.,meta.message). - Boundary markers: No explicit delimiters or boundary markers are defined to isolate untrusted data from the agent's instructions.
- Capability inventory: The skill is capable of executing the
swiggycommand-line tool with various subcommands and flags. - Sanitization: There is no evidence of sanitization, escaping, or validation of external content before it is processed or reported to the user.
Audit Metadata