report-writer
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
gitto retrieve commit logs and file diffs, and utilizes OS-specific commands (open,xdg-open,start) to launch the generated HTML report in the browser.\n- [EXTERNAL_DOWNLOADS]: Fetches CSS, font, and icon resources from reputable CDNs including Tailwind CSS, jsDelivr, and Google Fonts.\n- [PROMPT_INJECTION]: The skill ingests data from local git history to populate the report, which constitutes an indirect prompt injection surface.\n - Ingestion points: Git command outputs (
git diff,git log) collected in SKILL.md.\n - Boundary markers: None explicitly specified for the HTML token replacement.\n
- Capability inventory: File system write access and browser invocation via shell commands.\n
- Sanitization: No explicit sanitization or escaping instructions are provided for the gathered data.
Audit Metadata