workout
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to construct and execute shell commands using the
workoutCLI tool based on user-provided input. - Ingestion points: User-provided exercise names, muscle groups, equipment types, profile names, and notes as seen in
SKILL.md. - Capability inventory: Execution of subprocesses through the
workoutcommand-line utility. - Boundary markers: Absent. The instructions do not specify any delimiters or quoting mechanisms for handling user-supplied strings.
- Sanitization: Absent. The skill lacks instructions for validating or escaping shell metacharacters in user input before it is interpolated into commands like
workout logorworkout exercises add. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. Malicious instructions could be embedded within user data (such as exercise names or notes) to influence the agent's behavior during command generation or to bypass intended logic.
Audit Metadata