T09 · Insecure Skill Coding Practices
- Location
SKILL.md:109- Finding
Execution of Server-Supplied Update Commands
- Content
View full analysis
` with the directory of this installed Skill (the directory containing this Skill's SKILL.md). Never run `doctor` or a generic capability preflight to check freshness; the `update check` command above is the freshness check. Never ask more than once per component per session, and never substitute another command, flag, origin, or download path for the printed `action`. ``` ### Technical Analysis The Skill treats an `action` command returned by the remote PersonWise service as executable instructions. It requires user approval, but it does not require the Agent to validate the returned command against a locally defined grammar or allowlist before execution. Approval is not an adequate command-integrity boundary. A user may reasonably assume that the displayed command is a routine PersonWise update, while a compromised or malfunctioning service could return shell operators, an unexpected executable, unsafe arguments, or a command targeting unrelated local resources. This creates a command-injection trust boundary in which remote response data can become local code execution. The instructio ...[truncated 1587 chars]- Remediation
View remediation
