paniolo-scan
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
npx @paniolo/cli scanto generate a diagnostic report of the repository's AI harness. The command is used in a deterministic, read-only mode for scanning. - [EXTERNAL_DOWNLOADS]: The skill invokes the
@paniolo/clipackage vianpx, which involves downloading the package from the NPM registry. This package is an official vendor resource belonging to 'paniolo-ai'. - [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection as it processes external data to drive file modifications.
- Ingestion points: The agent reads and processes JSON output from the
@paniolo/clitool (SKILL.md). - Boundary markers: No explicit boundary markers or 'ignore' instructions are used when interpreting the tool's output.
- Capability inventory: The agent has the capability to write and edit files in the working tree to remediate findings (SKILL.md).
- Sanitization: The instructions do not specify sanitization or validation of the findings provided by the CLI tool before the agent performs file edits.
Audit Metadata