pipes-performance

Pass

Audited by Gen Agent Trust Hub on Mar 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses legitimate system tools (Read, Edit, Grep, Bash, BashOutput) for the intended purpose of analyzing indexer performance and modifying source code to implement optimizations.
  • [SAFE]: The skill references official documentation and datasets from the vendor's verified domains (sqd.dev and subsquid.io) to provide benchmarks and filtering guidance.
  • [PROMPT_INJECTION]: The skill identifies a potential surface for indirect prompt injection as it processes untrusted data. 1. Ingestion points: Reads source code and configuration from 'src/index.ts'. 2. Boundary markers: None present to distinguish instructions from user data in the input file. 3. Capability inventory: The skill has access to powerful tools like 'Bash' and 'Edit'. 4. Sanitization: No explicit sanitization of the input file content is performed. This is an inherent risk of the skill's primary function and is mitigated by the agent's internal safety guidelines.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 16, 2026, 05:28 AM