technical-analyst

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided chart images, which represents a potential attack surface for indirect prompt injection through text embedded within the visual data.
  • Ingestion points: Weekly timeframe chart images provided by the user as part of the analysis request (Step 1).
  • Boundary markers: The skill explicitly defines 'Pure Chart Analysis' and 'Objective Assessment' as core principles, instructing the agent to ignore all external factors and focus strictly on visible technical data.
  • Capability inventory: The skill's primary capability is writing markdown reports to a dedicated reports/ directory on the local filesystem.
  • Sanitization: The skill relies on strict instructional grounding and template-based output to ensure only relevant technical observations are included in the final report.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 07:50 AM