information-security-manager-iso27001
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, such as organizational asset inventories and threat models, creating a surface for instructions embedded in that data to influence agent behavior.
- Ingestion points: The skill instructions in
SKILL.mddirect the agent to perform 'Asset identification and classification' and 'Threat and vulnerability analysis' using external inputs. - Boundary markers: There are no specific delimiters or system instructions provided to help the agent distinguish between its core instructions and potentially malicious commands hidden within the data it is auditing.
- Capability inventory: The
SKILL.mdresource list identifies multiple automation scripts (incident-response-automation.py,isms-performance-dashboard.py) that, while missing from the current bundle, suggest the agent is intended to perform actions based on its analysis of external data. - Sanitization: The skill lacks any instructions or logic for validating, filtering, or sanitizing the content of the security documents or data feeds it processes.
Audit Metadata