factory-collect
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources (support tickets, chat logs, issue trackers) which could contain malicious instructions designed to influence the agent's behavior.\n
- Ingestion points: Processes content from sources defined in
.agent-factory/config.yaml, including support channels and telemetry.\n - Boundary markers: Lacks explicit instructions for the agent to ignore or delimit potentially malicious instructions within the collected feedback.\n
- Capability inventory: The skill allows for external actions such as replying to users and closing issues.\n
- Sanitization: No specific sanitization or escaping mechanisms are described for the ingested text.
Audit Metadata