skills/bigdra50/skills/html-reports/Gen Agent Trust Hub

html-reports

Pass

Audited by Gen Agent Trust Hub on Jul 5, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill employs shell scripts such as 'init.sh' and 'new-report.sh' to automate the creation of report directories and the generation of files from templates. These scripts use standard system commands like sed, awk, and cp to manage content within the project's local '.claude/reports/' directory.
  • [EXTERNAL_DOWNLOADS]: The generated HTML reports are configured to load standard visualization and syntax highlighting libraries (Mermaid, Prism.js, and Chart.js) from the well-known jsDelivr CDN (cdn.jsdelivr.net) at runtime.
  • [DATA_EXFILTRATION]: Analysis confirmed that the skill's operations are confined to the local project environment. There is no evidence of unauthorized data access or network-based exfiltration.
  • [PROMPT_INJECTION]: While the skill ingests project data to populate reports, this activity is restricted to the intended purpose of documentation. The risk of indirect prompt injection is minimized by the use of structured HTML templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 5, 2026, 01:15 PM
Security Audit — agent-trust-hub — html-reports