asc-subscriptions
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides numerous examples for managing App Store Connect resources using the
ascCLI tool, which is executed via the shell. - [INDIRECT_PROMPT_INJECTION]: The skill includes patterns for processing data that could originate from external sources.
- Ingestion points: The skill reads project metadata from
.asc/project.jsonand captures identifiers from the output ofasccommands usingjqfilters inSKILL.md. - Boundary markers: No specific delimiters or instructions to ignore embedded content are provided for the data being ingested.
- Capability inventory: The skill enables the agent to execute shell commands, read local files, and write outputs (e.g., saving redemption codes to
codes.csv). - Sanitization: The examples demonstrate direct interpolation of command outputs into variables without explicit sanitization steps.
Audit Metadata