skills/jeremylongshore/claude-code-plugins-plus-skills/implementing-backup-strategies/Gen Agent Trust Hub
implementing-backup-strategies
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by converting user-specified parameters into shell scripts.\n- Ingestion points: User-provided requirements and triggers for backup strategies processed by the agent in SKILL.md.\n- Boundary markers: Absent; no instructions are provided to the agent to delimit user data or ignore instructions embedded within the inputs.\n- Capability inventory: Shell execution via Bash (tar, rsync, aws) and extensive file system access (Read, Write, Edit, Grep, Glob) as defined in SKILL.md and referenced scripts.\n- Sanitization: Absent; there are no instructions for validating, escaping, or sanitizing user parameters before their interpolation into generated shell scripts.\n- [SAFE]: The use of persistence mechanisms such as cron jobs and systemd timers is the intended primary function for scheduling recurring backups and does not represent a security risk in this context.
Audit Metadata