analyze-performance
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze performance monitoring data from Sentry, which is an external source that could potentially be used to host malicious instructions.
- Ingestion points: Fetches performance metrics and transaction data using Sentry MCP tools as described in the command implementation section (SKILL.md).
- Boundary markers: The skill instructions do not specify delimiters or explicit instructions to treat the external Sentry data as untrusted or to ignore embedded commands.
- Capability inventory: The skill is configured to provide insights and suggest optimization opportunities based on the data; it does not contain code for file system modification, command execution, or unauthorized network requests.
- Sanitization: No mention of data sanitization, filtering, or validation is present in the instruction set.
Audit Metadata