performance-review

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted data from the local project environment, creating a potential surface for indirect prompt injection.\n- Ingestion points: Phases 1 and 2 instruct the agent to read source code, database schemas, migration files, query logs, and performance profiles.\n- Boundary markers: The instructions do not define any delimiters or provide warnings to the agent to ignore instructions that might be embedded within the data being analyzed.\n- Capability inventory: The skill can read files, execute a local Node.js script, spawn sub-agents, and modify files.\n- Sanitization: No sanitization or validation steps are defined for the ingested data.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 10:12 AM