context-management

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill utilizes Read, Grep, and Glob tools to ingest content from project files, which creates a surface for indirect prompt injection.
  • Ingestion points: Content ingested from local files via Read and Grep tools.
  • Boundary markers: No explicit boundaries or ignore-instructions are defined to prevent the agent from following directives embedded in read files.
  • Capability inventory: The skill allows the agent to Write to the filesystem.
  • Sanitization: No sanitization or input validation is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 04:23 PM