diagnosing-endpoint-performance
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from PostHog endpoint configurations, version histories, and SQL query logs, which provides a surface for indirect prompt injection if those data sources contain malicious instructions.
- Ingestion points: Tool outputs from
endpoint-get,endpoint-versions, andexecute-sqlas described in the workflow section ofSKILL.md. - Boundary markers: Absent; the instructions do not specify using delimiters or warnings to ignore instructions embedded in the telemetry data.
- Capability inventory: The skill uses
execute-sqlfor database queries and other tools to fetch or preview endpoint configurations. - Sanitization: Absent; the skill relies on the agent's internal logic to parse and interpret raw performance data.
Audit Metadata