troubleshooting-flows
Pass
Audited by Gen Agent Trust Hub on Jul 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill utilizes official 'celigo' CLI tools for troubleshooting integration flows. These are vendor-provided resources and do not represent a security risk.
- [PROMPT_INJECTION]: The skill instructions involve reading and analyzing external data such as error logs and record details from the Celigo platform (e.g., using 'celigo flows error --request-detail'). This constitutes a potential surface for indirect prompt injection, as malicious data processed by a flow could contain instructions meant to influence the agent. This is considered a low-risk inherent characteristic of troubleshooting data-processing systems. Evidence Chain: 1. Ingestion points: 'celigo flows errors', 'celigo flows error', 'celigo flows execution-logs', and 'celigo flows query-execution-logs' in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: 'celigo' CLI for flow management and log inspection in SKILL.md. 4. Sanitization: Absent.
Audit Metadata