review-data-analysis
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it requires the agent to read and execute untrusted external content, such as analysis scripts and notebooks.
- Ingestion points: Untrusted data enters the agent context through analysis code, notebooks, and raw data files as specified in Step 1, Step 3, and Step 5 of the procedure.
- Boundary markers: The skill lacks explicit instructions to use delimiters or ignore embedded instructions when processing external files.
- Capability inventory: The skill allows the use of potentially dangerous tools including
Bash,Read, andWebFetch(referenced in SKILL.md frontmatter). - Sanitization: There are no instructions for the agent to validate or sanitize the external code before execution in Step 5 (Assess Reproducibility).
Audit Metadata