analytics-data-analysis
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes workflows for loading and processing external data files (e.g., using
pd.read_csv), which establishes an attack surface for indirect prompt injection if data files contain malicious instructions. This risk is inherent to the skill's primary function of data analysis. - Ingestion points: Data loading instructions in SKILL.md.
- Boundary markers: Not mentioned for data content.
- Capability inventory: Reading local files and saving visualization images to the file system.
- Sanitization: The skill explicitly recommends checking data types, missing values, and implementing validation checkpoints.
Audit Metadata