rhel-fedora
Pass
Audited by Gen Agent Trust Hub on May 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides extensive access to system administration commands required for its primary purpose of managing RHEL-family distributions.
- Evidence: Frequent use of administrative tools including
dnf,rpm,systemctl,grubby,dracut,semanage, andfirewall-cmdthroughout all reference files. - Context: These commands are used as intended for package management, service troubleshooting, and boot configuration.
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection due to its requirement to read and process potentially untrusted external system data.
- Ingestion points: The agent is instructed to read output from
journalctl,ausearch,dmesg,rpm -qi, anddnf info, which may contain attacker-controlled content like malicious package descriptions or log entries. - Boundary markers: There are no explicit instructions or delimiters provided to the agent to distinguish between its instructions and the data being processed from system outputs.
- Capability inventory: The skill possesses high-privilege capabilities including package installation (
dnf), bootloader modification (grubby), and security policy changes (semanage,setsebool). - Sanitization: No sanitization or validation mechanisms are described for the data ingested from system commands before it is analyzed by the agent.
Audit Metadata