@6942/starchild-quests
Warn
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: MEDIUMREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill uses
search_skills(query, auto_install=true), allowing the agent to find and automatically execute external skills from a registry. This enables the execution of unverified third-party code. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes quest descriptions and skill search results without sanitization and uses this data to drive powerful actions. * Ingestion points: quest listing data and search results from the skill registry. * Boundary markers: Absent; the skill lacks instructions for the agent to ignore embedded instructions in the retrieved data. * Capability inventory: Shell command execution via curl, file writing to project directories, skill management (creation and publishing), and dynamic skill installation. * Sanitization: Absent; there is no evidence of filtering or validation of external content before it is processed by high-privilege tools.
Audit Metadata