review-ml-textbook
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes external data from potentially untrusted sources.
- Ingestion points: The skill workflow involves collecting and reading content from stable URLs of online technical references, bookdown/Quarto sites, and Jupyter Book sites (as specified in
SKILL.md). - Boundary markers: The instructions lack specific delimiters or warnings for the agent to treat external textbook content strictly as data and to ignore any embedded instructions.
- Capability inventory: The skill has the ability to spawn subagents, orchestrate global syntheses of findings, and generate or implement revision plans that could modify files (as specified in
SKILL.md). - Sanitization: There is no evidence of sanitization, filtering, or integrity verification of the content retrieved from external URLs before it is processed by the agent.
Audit Metadata