iblai-security-incident-triage
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze potentially untrusted data from a compromised system (e.g., logs and process outputs), which is a common vector for indirect prompt injection.
- Ingestion points: Data enters the agent's context through tools like
journalctl,ps,ss,who, andlsofas specified inSKILL.md. - Boundary markers: There are no explicit delimiters or instructions provided to isolate the forensic data from the agent's command processing.
- Capability inventory: The skill has access to
Bash,Read,Write, andGreptools, which allow it to interact with the host system and preserve evidence. - Sanitization: No specific sanitization or validation logic is applied to the forensic data before the agent interprets it.
- Contextual Note: Although this represents a potential attack surface, the behavior is strictly limited to the skill's primary and legitimate purpose of security forensics and triage.
Audit Metadata