agile-scrum
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the AI agent to execute shell commands (
ls) to inspect the local filesystem for existing installations and suggests the use ofnpxto install additional components like companion skills. - [DATA_EXFILTRATION]: The skill initiates environment discovery by directing the agent to probe for directory structures within the user's home folder (e.g.,
~/.claude/skills/,~/.agent/skills/). This unprompted access to the filesystem reveals information about the user's installed tools and configurations to the agent's processing context.
Audit Metadata