result-figure-consistencycheck
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external scientific paper text (e.g.,
inputs/paper_fulltext.md), which creates a vulnerability surface where adversarial instructions could be embedded in the data to influence the agent. - Ingestion points: Reads paper full-text provided in Markdown format.
- Boundary markers: While using
## Page XXheaders, the skill does not specify robust delimiters or instructions to ignore commands within the paper text. - Capability inventory: The skill has the capability to write consistency reports and CSV logs to the
outputs/directory. - Sanitization: No specific sanitization or filtering of input text for prompt injection is described.
- [EXTERNAL_DOWNLOADS]: The skill metadata references a source repository at
https://github.com/aipoch/medical-research-skills. This is a vendor-owned resource originating from the skill's author and is used for reference and source tracking.
Audit Metadata