update-cursor-settings
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and parse configuration files which can contain untrusted data.
- Ingestion points: The agent reads
settings.json(andcli-config.json) from the user's application support or configuration directories. - Boundary markers: The instructions lack explicit boundary markers or warnings to the agent to disregard any instructions found within the comments or values of the files being read.
- Capability inventory: The skill has the capability to read from and write to the local file system to alter application settings.
- Sanitization: No sanitization or validation of the input data from the configuration files is mentioned, allowing any embedded instructions to potentially influence the agent's behavior during the parsing process.
Audit Metadata