crontap-debug-failed-runs
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external schedule history and configuration data, which creates a surface where malicious instructions could be embedded in the ingested content to influence the agent.
- Ingestion points: The skill reads external data through the
get_scheduleandget_schedule_historytool outputs. - Boundary markers: Absent; there are no specific markers or instructions to isolate or treat external data as untrusted.
- Capability inventory: The skill is limited to diagnostic tool calls and reasoning, with no capabilities for file-system writing, network exfiltration of local data, or command execution.
- Sanitization: Absent; the instructions do not specify any filtering or sanitization of the API response data.
- [DATA_EXFILTRATION]: The skill includes a
curlcommand example in its documentation for accessing the officialapi.crontap.comendpoint. This is a neutral finding as it uses environment variables for authentication and targets verified vendor infrastructure.
Audit Metadata