tabular-review-antoine-louis
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill ingests untrusted data from external files and interpolates it into subagent prompts without proper security boundaries.
- Ingestion points: Step 3 uses the
pdfanddocxskills to read content from document paths discovered via theGlobtool. - Boundary markers: Absent. The subagent prompt template in Step 3 fails to use clear delimiters (such as XML tags or unique separators) to isolate the document text from the agent's instructions.
- Capability inventory: The skill utilizes the
Tasksystem for subagent execution, filesystem read access throughpdf/docxskills, and filesystem write access through thexlsxskill. - Sanitization: Absent. There is no logic provided to escape, filter, or validate the content extracted from the documents before it is processed by the LLM subagents.
Audit Metadata