asc-release-flow
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes local project data, including metadata directories and configuration files, which are passed as arguments to the
ascCLI tool. This creates an attack surface where untrusted content in the project repository could attempt to influence the agent's execution of release-related commands. - Ingestion points: The agent ingests data from local directories specified by
--metadata-dirand configuration files via--filearguments in SKILL.md. - Boundary markers: The instructions lack explicit delimiters or instructions for the agent to ignore potentially malicious embedded content within the ingested files.
- Capability inventory: The agent is instructed to execute various
ascCLI commands that interact with App Store Connect, including those that mutate version state and manage review submissions. - Sanitization: No evidence of data sanitization or validation is provided within the instructions before the project content is processed by the CLI tool.
Audit Metadata