be-jenkins-deploy
Pass
Audited by Gen Agent Trust Hub on May 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute platform-specific shell commands (PowerShell, osascript, and notify-send) to display notifications. These commands directly interpolate external variables such as branch names and job names without prior validation or escaping.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its handling of data from external systems.
- Ingestion points: The skill reads branch information from GitHub PRs via the
ghCLI and build status information from Jenkins job responses. - Boundary markers: No boundary markers or isolation techniques are employed to separate these external strings from the command logic.
- Capability inventory: The skill has the capability to perform shell executions on the host system to provide desktop notifications.
- Sanitization: There is no evidence of sanitization, filtering, or escaping for variables like
<branch>,<job>, or<RESULT>before they are passed to the shell environment.
Audit Metadata