linux-service-triage
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [Privilege Escalation] (LOW): The skill identifies and proposes administrative actions like
systemctl,chmod, andchownto fix service issues. This is consistent with its primary purpose, and the instructions include safety guardrails requiring user confirmation and starting with read-only diagnosis. - [Indirect Prompt Injection] (LOW): The skill processes untrusted data such as server logs and status outputs, which creates a surface for indirect prompt injection.
- Ingestion points:
SKILL.md(user-pasted logs and status output). - Boundary markers: Absent; the skill does not explicitly instruct the agent to ignore instructions embedded within the logs.
- Capability inventory:
references/triage-commands.md(contains commands for service management and permission modification). - Sanitization: Absent.
Audit Metadata