troubleshoot-cassandra
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted external data retrieved via monitoring tools and log inspection.
- Ingestion points: The skill utilizes MCP tools such as
query_metricsandfind_anomalous_metrics(documented in SKILL.md) and log files accessed viagrep(documented in rules/security-integrity.md) to bring external data into the agent's context. - Boundary markers: There are no explicit delimiters or instructions to treat ingested data as untrusted or to isolate it from the agent's internal reasoning and instruction following.
- Capability inventory: The agent is granted access to monitoring tools and filesystem logs, with the authority to recommend and potentially execute remediation actions based on the analysis of these external signals.
- Sanitization: No sanitization, validation, or escaping of the retrieved metrics or log entries is performed before the agent processes them.
Audit Metadata