helio-reading-report

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious code, obfuscation, or unauthorized execution patterns were detected. The skill instructions align with its stated purpose of research synthesis.
  • [EXTERNAL_DOWNLOADS]: The skill references documentation hosted on Google Drive. These are legitimate resources used for context and originate from a well-known service.
  • [PROMPT_INJECTION]: The skill is designed to analyze data from Helio reports. Although this creates a surface for indirect prompt injection, the risk is mitigated by the lack of high-privilege tool access within the skill's scope. 1. Ingestion points: Helio research reports (SKILL.md) 2. Boundary markers: Absent 3. Capability inventory: No high-risk tools (e.g., shell execution, file writing, or non-whitelisted network requests) are present in the skill definition 4. Sanitization: None specified
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 02:52 PM
Security Audit — agent-trust-hub — helio-reading-report