asc-game-center
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements a pattern where tool responses include "affordances" (ready-to-run commands) which the agent is encouraged to execute. This creates a surface for indirect prompt injection if the data returned by the App Store Connect API contains malicious instructions.
- Ingestion points: Instructions in
SKILL.mdprompt the agent to read and use commands found in JSON output fromasc game-centercalls. - Boundary markers: No delimiters or safety instructions are used to distinguish tool-generated commands from developer-vetted ones.
- Capability inventory: The skill enables execution of
ascCLI commands and shell pipelines involvingjq. - Sanitization: There is no evidence of sanitization or validation of the strings provided in the "affordances" field before they are interpreted as commands.
- [COMMAND_EXECUTION]: The skill relies on the
ascCLI tool to perform Game Center management tasks. It also utilizes shell scripts for data parsing and chaining commands, which represents a standard command execution capability.
Audit Metadata