asc-subscriptions
Pass
Audited by Gen Agent Trust Hub on May 1, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
ascCLI tool to perform administrative operations on App Store subscriptions, such as creating groups and listing localizations in SKILL.md. - [DATA_EXPOSURE]: The instructions describe reading the application identifier from a local project configuration file (
.asc/project.json), which is standard behavior for theascutility to determine context. - [PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection by processing data from configuration files and CLI outputs. 1. Ingestion points: Untrusted data enters via
.asc/project.jsonandasccommand outputs (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Subprocess execution viaasc,cat, andjq(SKILL.md). 4. Sanitization: Relies on structural extraction viajqbut lacks explicit sanitization or escaping of the extracted values before they are used in subsequent command arguments.
Audit Metadata