T05 · Unauthorized Access and Privilege Escalation
- Location
SKILL.md:33- Finding
Overbroad Access to Sensitive Operational Context
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
The skill is a coherent automation-audit helper, but it asks the agent to inspect sensitive local operational context without clear scope limits or redaction rules.
Review this carefully before installing. It is not trying to exfiltrate data or install code, but a normal run may inspect local scripts, scheduled tasks, API configuration, installed skills, and memory/context files. Use it only with explicit directory and data-category boundaries, and avoid allowing full secret values or private project context to be copied into generated reports.
SKILL.md:33Overbroad Access to Sensitive Operational Context
The manual trigger says to invoke the skill whenever 'the stack feels bloated' or reliability 'has degraded,' which are subjective conditions without clear boundaries. Combined with broad trigger phrases like 'what's still running?', this can cause unintended activation outside a narrowly defined audit context.
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
### 1. Crons — Are they alive and earning their keep?
For each launchd agent / cron job / scheduled task:
- Is the process actually running? (check PID, plist/cron status)
- When did it last fire successfully?
- What does it produce? Is that output being consumed by anything?
- Is there a newer/better approach that renders this obsolete?