paniolo-config-init
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends using the @paniolo/cli package, which is an official resource provided by the skill author paniolo-ai.
- [COMMAND_EXECUTION]: The skill suggests the execution of a shell command (npx --yes @paniolo/cli scan) to verify the generated configuration.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data by reading the content of paniolo.config.json and checking for the presence of various marker files in the repository.
- Ingestion points: The repo-level paniolo.config.json file and various file markers such as CLAUDE.md, .cursor/, and .devin/.
- Boundary markers: The skill instructions specify showing current values to the user before action, but do not employ specific prompt delimiters or "ignore embedded instructions" warnings for the ingested content.
- Capability inventory: The skill possesses file system write access (creating paniolo.config.json) and the ability to suggest shell command execution.
- Sanitization: The instructions do not define explicit sanitization or validation steps for the content read from the local files before it is processed or used to generate the new configuration.
Audit Metadata