engineering-report-generator
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill documentation and provided Python snippets focus on legitimate engineering report generation using established libraries (Pandas and Plotly).
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for ingesting external CSV data and generating HTML reports. While processing untrusted data is a theoretical attack surface, the provided code lacks autonomous execution patterns that would trigger an exploitation.
- Ingestion points: Reads data from
../data/processed/results.csvin SKILL.md. - Boundary markers: Not explicitly defined in code snippets.
- Capability inventory: File reading (
pandas.read_csv) and file writing (Path.write_text). - Sanitization: No explicit sanitization shown in template snippets.
- [COMMAND_EXECUTION]: File operations are limited to standard reading of CSV data and writing of HTML output using
pathlib, which is consistent with the skill's purpose.
Audit Metadata