csv-data-summarizer
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from CSV files and incorporates it directly into the agent's conversational context.
- Ingestion points: The Python script in
SKILL.mdusespd.read_csvto read user-provided files. - Boundary markers: The output summary does not use delimiters or protective instructions to isolate the data from the agent's primary instructions.
- Capability inventory: The skill has the ability to write files to the local filesystem using
plt.savefig. - Sanitization: The skill does not perform any validation or sanitization of the string content found within the CSV cells.
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of external Python libraries for its core functionality.
- Evidence: The documentation specifies
pip install pandas matplotlib seaborn. These are well-known and widely trusted data science libraries.
Audit Metadata