ea-results-analyser
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external, untrusted data in the form of primary research papers, PDFs, and discussion sections provided by the user. While the skill instructs the AI to follow a specific analysis structure, it lacks explicit boundary markers (such as XML tags or unique delimiters) to separate the untrusted document content from the skill's instructions.
- Ingestion points: Processes research papers, PDFs, and results/discussion sections provided by the user (as mentioned in the description and 'Handling PDFs' section).
- Boundary markers: Absent. The instructions do not specify a format for the input paper or how the agent should distinguish between the paper's text and its own instructions.
- Capability inventory: The skill only performs text analysis and formatting for markdown output. It does not possess capabilities for network operations, file writing, or command execution.
- Sanitization: Absent. There is no instruction to sanitize or filter the content of the research papers before processing.
Audit Metadata